US20100088242A1 - Method for mortgage fraud detection - Google Patents
Method for mortgage fraud detection Download PDFInfo
- Publication number
- US20100088242A1 US20100088242A1 US12/573,834 US57383409A US2010088242A1 US 20100088242 A1 US20100088242 A1 US 20100088242A1 US 57383409 A US57383409 A US 57383409A US 2010088242 A1 US2010088242 A1 US 2010088242A1
- Authority
- US
- United States
- Prior art keywords
- spatial
- property
- subject
- real property
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
- 238000000034 method Methods 0.000 title claims abstract description 81
- 238000001514 detection method Methods 0.000 title abstract description 6
- 230000002123 temporal effect Effects 0.000 claims description 32
- 239000011159 matrix material Substances 0.000 description 18
- 230000008901 benefit Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000002547 anomalous effect Effects 0.000 description 3
- 230000001174 ascending effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 230000003389 potentiating effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0278—Product appraisal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
- G06Q50/167—Closing
Definitions
- the present invention relates to a method of detecting fraud in loan application. More particularly, the present invention relates to a method of estimating the risk associated with a contemplated loan, and especially to estimating the risk that a lender may be induced to rely on an unrealistically high estimate of the value of the real property that is to secure the loan.
- AVMs automated valuation models
- a lender may also inquire whether the property has undergone certain patterns of frequent sales, loans or refinancings which have, in that lender's experience, come to be associated with attempts to cause artificially high estimates of the value of the property. Additionally, the lender may investigate the creditworthiness of the person applying for the loan. Finally, the lender might seek out information about the applicant's history, taking a particular interest in whether the applicant has been involved in a cluster of activities involving real property in the neighborhood.
- existing methods for fraud detection tend to emphasize either or both of (1) the history of the subject property (the property proposed for a sale or loan), with a special view to any possible “flipping” (rapid series of sales, loans, or refinances), and (2) the history and creditworthiness of the applicant, with a special view to any other transactions in the neighborhood of the subject property.
- an exemplary embodiment of a method for mortgage fraud prevention in accordance with the present invention comprises the steps of maintaining a database of sales prices in the computer system of a plurality of real properties in a geographic area in which the subject real property is located; obtaining from the computer system, valuation history data for the subject property; obtaining, using the computer system, historical sales data for property in the geographic area in which the subject real property is located; computing price ratio data using the valuation history for the subject property and the historical sales data for the subject property in the geographic area in which the subject property is located, and computing a distortion index based on the price ratio data to detect fraud in the mortgage application.
- the distortion index may include a temporal distortion index, a spatial distortion index, or a combination of these.
- the matrices of data that are assembled in the process of preparing the distortion index may also be reported.
- the method may be applied prospectively or retrospectively, with single properties or with large numbers of properties, and with the aid of varying automated valuation models.
- the method may be applied by a person far removed in time and place from the transaction in question and having no particular connection to it. Because a person using the method does not need to single out any neighborhood or other geographical area as a special danger area for fraud, the method in accordance with the present invention helps reduce the danger that a lender would be accused of improper exclusion, such as redlining.
- FIG. 1 is a block diagram of the overall process and information flow for an exemplary method of detecting mortgage fraud in accordance with the present invention
- FIG. 2 is a block diagram of input steps for an example of the method of detecting mortgage fraud in accordance with the present invention
- FIG. 3 is a block diagram of computation steps for an example of the method of detecting mortgage fraud in accordance with the present invention
- FIG. 4 is a block diagram of report steps for an example of the method of detecting mortgage fraud in accordance with the present invention.
- FIG. 5 is an exemplary set of matrices of data reported in accordance with the present invention.
- an exemplary embodiment of the method of detecting mortgage fraud in accordance with the present invention utilizes a general purpose computer with access to a database of sales price information pertaining to a geographical area where a parcel of real property is situated.
- the method obtains the identification of the subject property.
- the data processor 21 obtains from the requesting party 23 the location and characteristics of the property along with the proposed valuation of the property.
- the property characteristics and location are used to formulate a query to a database 27 of historical median price data for the zip code, city, and county in which the property is situated.
- the city may be the “postal city,” which is the default United States Postal Service city name for the subject property's zip code.
- the city may be the situs city, which includes the literal bounds of the city.
- the results of the query are used to create a matrix of spatial price information.
- the data processor 21 From the requesting party 23 or from the database 27 , the data processor 21 also obtains the time and price of a prior sale or valuation of the subject property. The data processor 21 passes this information to the automated valuation model 25 , which returns a set of yearly price values for the subject property. The data processor 21 then computes a spatial distortion index, a temporal distortion index, and a total distortion index. Finally, the data processor 21 reports at least the total distortion index to the requesting party.
- the exemplary embodiment of the method of detecting mortgage fraud in accordance with the present invention utilizes a general purpose computer with access to a database of sales price information pertaining to a geographical area where a parcel of real property is situated.
- the method in accordance with the present invention places the subject property and its requested or alleged value for the purpose of sale, loan, or refinance, within both a spatial and a temporal context.
- the method constructs a temporal context or “valuation history” for the subject property.
- This context is both real and virtual. It is real in that it includes all known valuations attributed to prior sales, appraisals, and refinances of the property. It is virtual in that it includes valuations of the property, done by an automated valuation model (AVM), valuing the property at regular intervals, such as yearly, back into the past.
- AVM automated valuation model
- the method also constructs a spatial context for the subject property at several geographic levels, obtaining median sale prices for the property's zip code, city, and county from a high-quality database, the data for which is usually obtained from the county recorder's office.
- the database is queried for data pertinent to properties sharing the characteristics of the subject property. For example, if the subject property is a single family residence, the database is queried for single family residences. If the property is a condominium or townhouse and appropriately specific data are available, the query will reflect this information. These prices are extracted for the present and the past, for the time periods used in building the temporal context.
- the temporal and spatial contexts together build a price level matrix.
- One column of the matrix constitutes the prices of the subject property's temporal context.
- the other columns of the matrix are built from the prices of the various levels of the spatial context.
- the rows of this matrix are assigned to the time periods of the temporal context; the columns represent the concentric levels of the spatial context.
- the entries in the matrix represent the ratios of price levels (for the different time periods) of subject property to zip code prices, subject property to city prices, subject property to county prices, zip code to city, and city to county.
- Ratios outside of reasonable contextual levels are said to be distorted.
- reasonable variations are possible in the absence of fraud.
- Individual properties can be more or less valuable than the main body of properties in their zip code, city, or county.
- Prices in a zip code or city can be higher or lower than those in their corresponding city or county.
- the ratios can also vary according to basic principles of the business cycle. For instance, it is generally accepted that during boom times prices in affluent areas rise in greater proportions than do prices in middle-class or poor areas, whereas during declining markets, prices in affluent areas are subject to disproportionate declines. Furthermore, price trends in affluent areas tend to “lead” the rest of the market in that they pull out of a recession, or stop rising near the end of a boom, before the main body of the market does so.
- Abnormal or distorted ratios may suggest the possibility of fraud in a loan application, and indicate the wisdom of further investigation such as an outside appraisal. If the past history of a subject property suggests that its valuation is between 100% and 120% of the median value in its zip code, but the last two loan's on the property were based on valuations which were first 180% and then 250% of the median value in the zip code, this spatial ratio distortion may suggest the possibility of fraud. In the same way, if prices in the property's zip code have been rising at 5% to 7% per year for the past few years, but the alleged valuations of the subject property represent an increase of 40% over the previous year's valuation, this temporal ratio distortion may suggest the possibility of fraud.
- the individual temporal ratio distortions and spatial ratio distortions can be used to construct a distortion ratio score which may be expressed in numerical or letter-grade form to suggest the presence of unusual numbers and the possibility of fraud.
- an example of the method of detecting mortgage fraud in accordance with the present invention utilizes a general purpose computer with access to a database of sales price information pertaining to a geographical area where a parcel of real property is situated.
- the process begins when information is obtained as shown at reference number 41 about the subject property including its address, the identity of its owner, and physical attributes such as the type of structure, square footage, lot size, and the like. Also obtained (see at 43 ) is the valuation that is being requested or proposed by the applicant.
- the process will now be described by way of example as of a time-point of Jul. 1, 2003 for two proposed market values: a realistic value and an unrealistically high value. In this example, it will be assumed that for the property involved, a value of $400,000 is reasonable and $550,000 is unrealistically high.
- the process next obtains data about previous sales, appraisals, or refinance valuations for the subject property, along with date and source of those valuations.
- the subject property was sold in 1994 for $180,000. This prior sale may be represented as follows:
- the process next calls upon an automated valuation model to produce a valuation of the subject property as of the date of the request and at one-year intervals into the past to the extent permitted by the available data.
- the automated valuation model being used is ValuePoint®4 (“VP4”), a well-known service provided by First American Real Estate Solutions. It can be seen that the VP4 automated valuation model has generated a series of estimated price values for the subject property for Jul. 1, 1999 ($268,000) through Jul. 1, 2003 ($395,000). These data, which we may refer to as temporal information concerning the subject property, may be tabulated as follows:
- the process next builds one or more columns of information about the economic performance of other properties having various spatial relationships to the subject property.
- the process builds columns of median price data for properties having characteristics similar to those of the subject property.
- median price data are obtained for properties of the same type as the subject property, such as “single-family residence” or “condominium/townhouse.” Further refinements based on studying detailed property characteristics are also possible.
- These data are obtained or computed from a database of available reported sales, appraisals, and the like in the same zip code, postal city, and county as the subject property.
- the postal city is the default city name as used by the United States Postal Service for the zip code in which the property is situated.
- the situs city of the subject property could be used: the city inside whose borders the subject property is legally situated.
- the process unites the information into a spatial price median matrix, which may be tabulated as follows:
- the process computes ratios of the subject property value (price) to the median value reported in the various reference data sets (here, the reference data sets are the median price data for the same zip code, same postal city, and same county as the subject property).
- the result which may be referred to as a matrix of spatial variances, may be tabulated as follows:
- the ratios may be measured arithmetically by division.
- a comparison by way of division of the realistic and unrealistic value ratios of the subject property divided by their respective maximum prior ratios are as follows:
- the process generates a matrix of temporal variances by computing the following ratios for each time period:
- “One year prior” in this example means the complete year previous to the year in question.
- the temporal variances are tabulated as follows:
- the process identifies distortions that are associated with the subject property valuation.
- the process may use the subject to city ratio or the subject to county ratio in place of the subject to zip ratio.
- the process computes a temporal distortion, which is defined as the percentage change in subject valuation from the prior year, minus the percentage change in the zip code valuation from the prior year.
- a temporal distortion is defined as the percentage change in subject valuation from the prior year, minus the percentage change in the zip code valuation from the prior year.
- the process may use the subject to city ratio or the subject to county ratio in place of the subject to zip ratio.
- an alternative index of temporal distortion is computable as the ratio of the percentage change in subject valuation from the prior year to the percentage change in the zip code valuation from the prior year. For the purposes of the present example, however, this alternative distortion index will not be used in the subsequent steps of the process.
- the process computes the total distortion, which is defined as the sum of the spatial and temporal distortions.
- the process reports this total distortion to the customer.
- the reported information also includes the spatial and temporal components individually and, if it is deemed appropriate, some or all of the matrix data that gave rise to the computation as shown in FIG. 5 .
- a total distortion above 50% usually suggests an unrealistic valuation and hence a possible fraud.
- a total distortion above 100% almost always merits further investigation.
- the process allows the customer to specify any desired total distortion value which would flag an application as likely to be fraudulent.
- the price, ratio, and distortion matrices can be offered as supporting documentation. If no fraud is suspected, this step will usually not be necessary. If a fraud is suspected, this supporting documentation can be very useful to support and guide any lending or other decision. It is a particular advantage of the present invention that it avoids the inference of redlining or other geographic discrimination, because the person using the method does not need to single out any neighborhood or other geographical area as a special danger area for fraud and because the data produced in accordance with the present invention is “mechanistic” rather than subjective or personal.
- FIG. 5 exemplifies documentation the present invention makes available where a valuation is suspected to be fraudulent. Such information can be delivered efficiently to the customer along with other information such as the proposed valuation and the name address of the applicant and the address and relevant information concerning the subject property.
- lenders will be satisfied with such a score or grade, especially if the findings suggest normal price levels and thus a low likelihood of fraud. In some cases, lenders will request the supporting documentation of the price level matrix and price ratio matrix, especially in cases where a high distortion ratio score suggests the possibility of fraud.
- the requirements of the method in accordance with the present invention are not the same as the requirements of existing fraud detection methods.
- the requirements are twofold: (1) the availability of a high quality automated valuation model (AVM) which is able to value a subject property in current time and at selected times in the past; and (2) a database of median price statistics at several geographic levels such as the zip code, city, and county where the subject property is situated.
- AVM automated valuation model
- the method in accordance with the present invention astutely combines these two components to provide a number of advantages over existing fraud detection methods.
- the method in accordance with the present invention can provide documentation if a lender is called upon to support a decision on a loan application. The efficiency of automated data processing reduces the cost of producing such documentation when it is called for.
- the scores and matrices produced by the method in accordance with the present invention can be requested and transmitted in an automated fashion for one property at a time or for thousands or millions of properties.
- the method can be used whenever needed, for subject properties and applications throughout the country. Thus, the method can achieve economies of scale.
- An entire bundle of loans may be analyzed pursuant to one request.
- the loans may be proposed loans, or they may be loans that were made in the past.
- the fraud sought to be detected may be prospective, or it may already have occurred.
- One may, therefore, use the present invention to re-evaluate the risk entailed in choices that were made in the past or that were made by others who, at the time, had a very different appreciation of the sensitivity and selectivity with which others later would evaluate the risk of fraud.
- the method in accordance with the present invention also embodies a recognition of the tactics and limitations of the perpetrators of mortgage fraud, with a view to making fraud much more difficult to accomplish and rendering fraudulent alleged values easier to detect.
- perpetrators of fraud (“fraudsters”) are frequently able to arrange a series of real or alleged sales, appraisals, or loans for a subject property, often at ascending valuation levels, to support their claims of value for a sale or loan.
- Fraudsters also often arrange a series of real or alleged sales, appraisals, or loans for a set of properties in a single neighborhood, often at ascending valuation levels, to support their claims of ascending market valuations or prices, and to support their alleged valuation of a subject property for the purposes of a sale or loan.
- fraudsters will not have the resources to arrange enough false valuations or false sale prices to distort the overall price levels in a well-populated zip code, much less in an entire city or county, because there are many legitimate sales in such areas. Fraudsters also probably will not have the persistence to arrange a history of false valuations or prices on a subject property that extends several years into the past. In general, fraudsters are unlikely to spend three, five, or more years to build a trail of false valuations of a subject property. Combining a spatial distortion index with a temporal distortion index places the concealment of the attempted fraud beyond the resources and beyond the patience of fraudsters.
- an advantage of the method in accordance with the present invention is that it uses a combination of distortion ratio methods to differentiate realistic valuations, which are likely to result from underlying market phenomena, from various types of unrealistic valuations that are likely to result from the behaviors that fit the methods and motivations of fraudsters.
- the various advantages of the method combine to result in a substantial, novel, non-obvious advance over existing methods of detecting fraud in a mortgage application.
- the method in accordance with the present invention is also useful in identifying past transactions which gave rise to anomalous valuations. For example, one may wish to investigate the history of a particular property not only for indications of mortgage fraud, but also for indications that any party to a transaction recognized a value inconsistent with market conditions.
- a database of valuation-generating events is maintained in a computer system for a plurality of real properties in a geographic area in which the subject real property is located.
- a valuation-generating event may be a sale, a valuation pursuant to a mortgage application, or any other event indicating a value placed on the property by any party.
- a subject property record set including a price (or other valuation) of the property and the date thereof for at least one valuation-generating event is obtained from the computer.
- a valuation history data set for the subject property, comprising prices and the dates thereof for several timepoints, is obtained from the computer. This step may involve obtaining values generated by automated valuation models as well as values derived from other sources of data.
- historical sales data for property in the geographic area in which the subject real property is located is obtained from the computer.
- This data is obtainable, for example, from county recorders.
- a database query may be formulated comprising such information as the location, type, and other economically important characteristics of the subject property, to the extent appropriate in light of the available data.
- price ratio data is computed using the valuation history for the subject property and the historical sales data for the subject property in the geographic area in which the subject property is located. Also in the manner described herein, a distortion index is computed based on the price ratio data to detect an anomalous valuation in the at least one valuation generating event.
- a distortion index is computed and displayed for each of a plurality of conditions so that patterns and relationships may be revealed. For example, for a single identified property the distortion index may be reported as a function of time. Alternatively, a particular timeframe may be selected and the distortion index may be reported as a function of other variables or combinations of variables.
- the variables may include, for example, the identity of the transferor or the transferee, the identity of the lender or loan officer, the geographical location, the municipal jurisdiction, or any other descriptive information associated with the property or with the transaction. It is possible, therefore, to associate certain individuals, brokers, lenders, environments or timeframes with certain valuation patterns that signal an anomalous valuation.
- the method in accordance with the present invention becomes a potent tool for risk management in secondary sales of financial instruments, as well as for historical and economic research and other investigative purposes.
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
A method of detection of fraud in a mortgage application: in a computer system, maintaining a database of sales prices of real properties in a geographic area where the property is located; obtaining a valuation history for the property; obtaining historical sales data for similar properties in the geographic area; computing price ratios using these valuation histories; computing a distortion index based on the price ratios, the distortion index indicating the likelihood of a fraudulent valuation.
Description
- This application is a continuation of and claims the benefit and priority of application Ser. No. 10/713,348, entitled “Method for Mortgage Fraud Detection,” filed Nov. 14, 2003, now U.S. Pat. No. 7,599,882, which is assigned to the assignee hereof and hereby expressly incorporated by reference herein.
- 1. Field
- The present invention relates to a method of detecting fraud in loan application. More particularly, the present invention relates to a method of estimating the risk associated with a contemplated loan, and especially to estimating the risk that a lender may be induced to rely on an unrealistically high estimate of the value of the real property that is to secure the loan.
- 2. Description of the Related Art
- For the purpose of controlling the risk associated with lending money secured by real property, a loan originator attempts to estimate the value of the property being used to secure the note. Traditionally, the originator paid an appraiser, who was supposed to be knowledgeable in the type of real property in question and skilled in comparing such properties, and relied on the appraiser's estimate of the market value of the real property in order to limit the risk that value would be inadequate to secure the note. The use of appraisals continues. In recent years, lenders who wish to rely less on the appraisal have begun using “automated valuation models” (“AVMs”), methods of estimating the market value of a property based on various methodologies such as price indexing methods, hedonic models, adjusted tax assessed value models, and hybrid models.
- A lender may also inquire whether the property has undergone certain patterns of frequent sales, loans or refinancings which have, in that lender's experience, come to be associated with attempts to cause artificially high estimates of the value of the property. Additionally, the lender may investigate the creditworthiness of the person applying for the loan. Finally, the lender might seek out information about the applicant's history, taking a particular interest in whether the applicant has been involved in a cluster of activities involving real property in the neighborhood.
- Thus, existing methods for fraud detection tend to emphasize either or both of (1) the history of the subject property (the property proposed for a sale or loan), with a special view to any possible “flipping” (rapid series of sales, loans, or refinances), and (2) the history and creditworthiness of the applicant, with a special view to any other transactions in the neighborhood of the subject property.
- These methods are not infallible. An appraiser charges a hefty fee, usually requires several days or more to deliver an appraisal, and occasionally turns out to be incompetent, gullible, or corrupt. Persons attempting to inflate the estimated value of a property have been known to engage in patterns of sham sales of the subject property or of nearby properties. They may also act in concert with others to create in the mind of a purchaser or a lender a false impression that properties in the area are appreciating rapidly. Such tactics might also have the effect of feeding artificially inflated values to the automated valuation models that the lender is relying on.
- An inexperienced or careless loan officer may be taken in by such schemes. Unfortunately, even a more wary loan officer may hesitate to deny the application or to demand additional information. Lenders are under pressure to avoid the appearance that they are engaging in unfair discrimination against classes of applicants or against neighborhoods which are perceived to be underserved by the banking industry. The lender may fear being sued and being forced at great expense to prove an objective basis for denying an application.
- It is therefore necessary for lenders to have more efficient, reliable, to objective means of controlling the risk of being victimized by mortgage fraud.
- It is an object of the present invention to improve a lender's ability to control the risks associated with mortgage fraud while also controlling the costs of avoiding those risks.
- In accordance with these objects and with others which will be described and which will become apparent, an exemplary embodiment of a method for mortgage fraud prevention in accordance with the present invention comprises the steps of maintaining a database of sales prices in the computer system of a plurality of real properties in a geographic area in which the subject real property is located; obtaining from the computer system, valuation history data for the subject property; obtaining, using the computer system, historical sales data for property in the geographic area in which the subject real property is located; computing price ratio data using the valuation history for the subject property and the historical sales data for the subject property in the geographic area in which the subject property is located, and computing a distortion index based on the price ratio data to detect fraud in the mortgage application.
- The distortion index may include a temporal distortion index, a spatial distortion index, or a combination of these.
- The matrices of data that are assembled in the process of preparing the distortion index may also be reported.
- The method may be applied prospectively or retrospectively, with single properties or with large numbers of properties, and with the aid of varying automated valuation models.
- The method may be applied by a person far removed in time and place from the transaction in question and having no particular connection to it. Because a person using the method does not need to single out any neighborhood or other geographical area as a special danger area for fraud, the method in accordance with the present invention helps reduce the danger that a lender would be accused of improper exclusion, such as redlining.
- For a further understanding of the objects and advantages of the present invention, reference should be had to the following detailed description, taken in conjunction with the accompanying drawing, in which like parts are given like reference numbers and wherein:
-
FIG. 1 is a block diagram of the overall process and information flow for an exemplary method of detecting mortgage fraud in accordance with the present invention; -
FIG. 2 is a block diagram of input steps for an example of the method of detecting mortgage fraud in accordance with the present invention; -
FIG. 3 is a block diagram of computation steps for an example of the method of detecting mortgage fraud in accordance with the present invention; -
FIG. 4 is a block diagram of report steps for an example of the method of detecting mortgage fraud in accordance with the present invention; and -
FIG. 5 is an exemplary set of matrices of data reported in accordance with the present invention. - With reference to
FIG. 1 , an exemplary embodiment of the method of detecting mortgage fraud in accordance with the present invention utilizes a general purpose computer with access to a database of sales price information pertaining to a geographical area where a parcel of real property is situated. The method obtains the identification of the subject property. Thedata processor 21 obtains from the requestingparty 23 the location and characteristics of the property along with the proposed valuation of the property. The property characteristics and location are used to formulate a query to a database 27 of historical median price data for the zip code, city, and county in which the property is situated. The city may be the “postal city,” which is the default United States Postal Service city name for the subject property's zip code. Alternatively, the city may be the situs city, which includes the literal bounds of the city. The results of the query are used to create a matrix of spatial price information. From the requestingparty 23 or from the database 27, thedata processor 21 also obtains the time and price of a prior sale or valuation of the subject property. Thedata processor 21 passes this information to theautomated valuation model 25, which returns a set of yearly price values for the subject property. Thedata processor 21 then computes a spatial distortion index, a temporal distortion index, and a total distortion index. Finally, thedata processor 21 reports at least the total distortion index to the requesting party. - The exemplary embodiment of the method of detecting mortgage fraud in accordance with the present invention utilizes a general purpose computer with access to a database of sales price information pertaining to a geographical area where a parcel of real property is situated.
- The method in accordance with the present invention places the subject property and its requested or alleged value for the purpose of sale, loan, or refinance, within both a spatial and a temporal context.
- The method constructs a temporal context or “valuation history” for the subject property. This context is both real and virtual. It is real in that it includes all known valuations attributed to prior sales, appraisals, and refinances of the property. It is virtual in that it includes valuations of the property, done by an automated valuation model (AVM), valuing the property at regular intervals, such as yearly, back into the past.
- The method also constructs a spatial context for the subject property at several geographic levels, obtaining median sale prices for the property's zip code, city, and county from a high-quality database, the data for which is usually obtained from the county recorder's office. The database is queried for data pertinent to properties sharing the characteristics of the subject property. For example, if the subject property is a single family residence, the database is queried for single family residences. If the property is a condominium or townhouse and appropriately specific data are available, the query will reflect this information. These prices are extracted for the present and the past, for the time periods used in building the temporal context.
- In accordance with the present invention, the temporal and spatial contexts together build a price level matrix. One column of the matrix constitutes the prices of the subject property's temporal context. The other columns of the matrix are built from the prices of the various levels of the spatial context.
- From the price level matrix it is possible to construct a price ratio matrix. The rows of this matrix are assigned to the time periods of the temporal context; the columns represent the concentric levels of the spatial context. The entries in the matrix represent the ratios of price levels (for the different time periods) of subject property to zip code prices, subject property to city prices, subject property to county prices, zip code to city, and city to county.
- Ratios outside of reasonable contextual levels are said to be distorted. In the price ratio matrix, reasonable variations are possible in the absence of fraud. Individual properties can be more or less valuable than the main body of properties in their zip code, city, or county. Prices in a zip code or city can be higher or lower than those in their corresponding city or county. The ratios can also vary according to basic principles of the business cycle. For instance, it is generally accepted that during boom times prices in affluent areas rise in greater proportions than do prices in middle-class or poor areas, whereas during declining markets, prices in affluent areas are subject to disproportionate declines. Furthermore, price trends in affluent areas tend to “lead” the rest of the market in that they pull out of a recession, or stop rising near the end of a boom, before the main body of the market does so.
- Abnormal or distorted ratios may suggest the possibility of fraud in a loan application, and indicate the wisdom of further investigation such as an outside appraisal. If the past history of a subject property suggests that its valuation is between 100% and 120% of the median value in its zip code, but the last two loan's on the property were based on valuations which were first 180% and then 250% of the median value in the zip code, this spatial ratio distortion may suggest the possibility of fraud. In the same way, if prices in the property's zip code have been rising at 5% to 7% per year for the past few years, but the alleged valuations of the subject property represent an increase of 40% over the previous year's valuation, this temporal ratio distortion may suggest the possibility of fraud.
- The individual temporal ratio distortions and spatial ratio distortions can be used to construct a distortion ratio score which may be expressed in numerical or letter-grade form to suggest the presence of unusual numbers and the possibility of fraud.
- With reference to
FIGS. 2-5 , an example of the method of detecting mortgage fraud in accordance with the present invention utilizes a general purpose computer with access to a database of sales price information pertaining to a geographical area where a parcel of real property is situated. - With particular reference to
FIG. 2 , the process begins when information is obtained as shown atreference number 41 about the subject property including its address, the identity of its owner, and physical attributes such as the type of structure, square footage, lot size, and the like. Also obtained (see at 43) is the valuation that is being requested or proposed by the applicant. The process will now be described by way of example as of a time-point of Jul. 1, 2003 for two proposed market values: a realistic value and an unrealistically high value. In this example, it will be assumed that for the property involved, a value of $400,000 is reasonable and $550,000 is unrealistically high. - At this point, the proposed value and the time of the proposed value may be tabulated for the two alternative values as follows:
-
TIME PRICE COMMENT Jul. 1, 2003 $400,000 realistic requested Jul. 1, 2003 $550,000 unrealistic requested - With reference to
FIG. 3 , at 45, the process next obtains data about previous sales, appraisals, or refinance valuations for the subject property, along with date and source of those valuations. In this example, the subject property was sold in 1994 for $180,000. This prior sale may be represented as follows: -
TIME PRICE COMMENT 1994 $180,000 prior sale - The process next calls upon an automated valuation model to produce a valuation of the subject property as of the date of the request and at one-year intervals into the past to the extent permitted by the available data. In this example, the automated valuation model being used is ValuePoint®4 (“VP4”), a well-known service provided by First American Real Estate Solutions. It can be seen that the VP4 automated valuation model has generated a series of estimated price values for the subject property for Jul. 1, 1999 ($268,000) through Jul. 1, 2003 ($395,000). These data, which we may refer to as temporal information concerning the subject property, may be tabulated as follows:
-
TIME PRICE COMMENT 1994 $180,000 prior sale 1995 1996 1997 1998 1999 $268,000 automated value - VP4 AVM for July 1 2000 $276,000 automated value - VP4 AVM for July 1 2001 $335,000 automated value - VP4 AVM for July 1 2002 $371,000 automated value - VP4 AVM for July 1 2003 $395,000 automated value - VP4 AVM for July 1 2003 $400,000 Requested July - realistic 2003 $550,000 Requested July - unrealistic - At 47, the process next builds one or more columns of information about the economic performance of other properties having various spatial relationships to the subject property. In this example, the process builds columns of median price data for properties having characteristics similar to those of the subject property. For example, median price data are obtained for properties of the same type as the subject property, such as “single-family residence” or “condominium/townhouse.” Further refinements based on studying detailed property characteristics are also possible. These data are obtained or computed from a database of available reported sales, appraisals, and the like in the same zip code, postal city, and county as the subject property. The postal city is the default city name as used by the United States Postal Service for the zip code in which the property is situated. Alternatively, the situs city of the subject property could be used: the city inside whose borders the subject property is legally situated.
- These median price statistics are to come from a standard and reliable source. These numbers must apply to the same type of residential property as the subject property (single-family residence, or condo/townhouse, etc.). These numbers are for time periods to correspond with the months and years that appear in the subject property columns. For dates in the most recent year, the process uses tri-monthly medians for the most recent completed three months. For dates in previous years, the process uses yearly medians.
- The process unites the information into a spatial price median matrix, which may be tabulated as follows:
-
PRICE OF PRICE OF PRICE OF PRICE OF PROPERTIES PROPERTIES PROPERTIES SUBJECT IN SAME IN SAME IN SAME TIME PROPERTY ZIP CODE POSTAL CITY COUNTY 1994 $180,000 $175,000 $150,000 $160,000 1995 $167,000 $139,000 $153,000 1996 $163,000 $134,500 $150,000 1997 $178,000 $136,000 $150,000 1998 $195,000 $138,000 $162,000 1999 $268,000 $244,000 $142,000 $175,000 2000 $276,000 $261,000 $149,000 $192,000 2001 $335,000 $310,000 $170,000 $229,000 2002 $371,000 $388,000 $220,000 $267,000 2003 $395,000 $410,000 $241,000 $297,000 2003 $400,000 (proposed) 2003 $550,000 (proposed) - At 49, for each time value (each year), the process computes ratios of the subject property value (price) to the median value reported in the various reference data sets (here, the reference data sets are the median price data for the same zip code, same postal city, and same county as the subject property). The result, which may be referred to as a matrix of spatial variances, may be tabulated as follows:
-
RATIO, %, RATIO, %, RATIO, %, RATIO, %, RATIO, %, RATIO, %, SUBJECT SUBJECT SUBJECT ZIP TO ZIP TO CITY TO TIME TO ZIP TO CITY TO COUNTY CITY COUNTY COUNTY 1994 103 120 113 117 109 94 1995 120 109 91 1996 121 109 90 1997 131 119 91 1998 141 120 85 1999 110 189 153 172 139 81 2000 106 185 144 175 136 78 2001 108 197 146 182 135 74 2002 96 169 139 176 145 82 2003 96 164 133 170 138 81 2003* 98 166 135 170 138 81 2003** 134 228 185 170 138 81 *proposed realistic value **proposed unrealistic value - From this table, it is evident that the historical value and the automated valuation of the subject property are typical of the values of similar properties in the zip code. It also appears that such properties in the subject property's zip code are more expensive than those in the city or county as a whole, and have risen faster in recent years than those in the city or county as a whole.
- It also is evident that the ratios computed from the unrealistic valuation (134%, 228%, 185%) stand out somewhat from the rest of the matrix. The unrealistic valuation is apparent when measured arithmetically by subtraction. For example, by way of subtraction, 134% is 24% higher than 110%, the maximum ratio found in the column above it. Similarly, 228% is 31% higher than 197%, the maximum ratio in the column above it, and 185% is 32% higher than 153%, the maximum ratio in the column above it.
- Alternatively, the ratios may be measured arithmetically by division. For example, a comparison by way of division of the realistic and unrealistic value ratios of the subject property divided by their respective maximum prior ratios are as follows:
-
Realistic Unrealistic 98%/110% = 89% 134%/110% = 122% 166%/197% = 84% 228%/197% = 116% 135%/153% = 88% 185%/153% = 121% - For purposes of the present example, however, this alternative measurement of ratios by division will not be used in the subsequent steps of the process.
- At 53, the process generates a matrix of temporal variances by computing the following ratios for each time period:
-
- Subject value to subject value one year prior;
- Zip code median to zip code median one year prior;
- City median to city median one year prior; and
- County median to county median one year prior.
- “One year prior” in this example means the complete year previous to the year in question. The temporal variances are tabulated as follows:
-
ratio, ratio, ratio, ratio, %, subject, %, zip, %, city, %, county, over year over year over year over year time previous previous previous previous 1994 1995 95 93 96 1996 98 97 98 1997 109 101 100 1998 110 101 108 1999 125 103 108 2000 103 107 105 110 2001 121 119 114 119 2002 111 125 129 117 2003 106 106 110 111 2003* 108 106 110 111 2003** 148 106 110 111 *proposed realistic value **proposed unrealistic value - It is noticeable that the temporal variance associated with the unrealistic valuation (148%) stands out as inconsistent with the rest of the matrix, while the temporal variance associated with the realistic valuation (108%) does not.
- At 51, the process identifies distortions that are associated with the subject property valuation. The spatial distortion is the amount that the subject to zip ratio exceeds the maximum of the entries in the column above it. For the realistic valuation of $400,000, that distortion is zero, since 98% does not exceed 110%. For the unrealistic valuation of $550,000, that distortion is 24%, since 134%−110%=24%.
- In some zip codes, there might not be enough data on historical prices of comparable properties to produce a reliable matrix. In such a situation, where, for example, the average number of sales in a zip code per year is less than 100, the process may use the subject to city ratio or the subject to county ratio in place of the subject to zip ratio.
- At 55, the process computes a temporal distortion, which is defined as the percentage change in subject valuation from the prior year, minus the percentage change in the zip code valuation from the prior year. For the realistic valuation, the temporal distortion is 108%−106%=2%. For the unrealistic valuation, the temporal distortion is 148%−106%=42%. As before, if the average number of sales in a zip code per year is less than 100, the process may use the subject to city ratio or the subject to county ratio in place of the subject to zip ratio.
- It should be pointed out that an alternative index of temporal distortion is computable as the ratio of the percentage change in subject valuation from the prior year to the percentage change in the zip code valuation from the prior year. For the purposes of the present example, however, this alternative distortion index will not be used in the subsequent steps of the process.
- At 57, the process computes the total distortion, which is defined as the sum of the spatial and temporal distortions. For the legitimate valuation, the total distortion is 0%+2%=2%. For the fraudulent valuation, it is 24%+42%=66%.
- With reference to
FIG. 4 , at 59, the process reports this total distortion to the customer. Optionally, at 61, the reported information also includes the spatial and temporal components individually and, if it is deemed appropriate, some or all of the matrix data that gave rise to the computation as shown inFIG. 5 . - A total distortion above 50% usually suggests an unrealistic valuation and hence a possible fraud. A total distortion above 100% almost always merits further investigation.
- Optionally, the process allows the customer to specify any desired total distortion value which would flag an application as likely to be fraudulent.
- If the customer or user requests it, the price, ratio, and distortion matrices can be offered as supporting documentation. If no fraud is suspected, this step will usually not be necessary. If a fraud is suspected, this supporting documentation can be very useful to support and guide any lending or other decision. It is a particular advantage of the present invention that it avoids the inference of redlining or other geographic discrimination, because the person using the method does not need to single out any neighborhood or other geographical area as a special danger area for fraud and because the data produced in accordance with the present invention is “mechanistic” rather than subjective or personal.
-
FIG. 5 exemplifies documentation the present invention makes available where a valuation is suspected to be fraudulent. Such information can be delivered efficiently to the customer along with other information such as the proposed valuation and the name address of the applicant and the address and relevant information concerning the subject property. - Many lenders will be satisfied with such a score or grade, especially if the findings suggest normal price levels and thus a low likelihood of fraud. In some cases, lenders will request the supporting documentation of the price level matrix and price ratio matrix, especially in cases where a high distortion ratio score suggests the possibility of fraud.
- The requirements of the method in accordance with the present invention are not the same as the requirements of existing fraud detection methods. The requirements are twofold: (1) the availability of a high quality automated valuation model (AVM) which is able to value a subject property in current time and at selected times in the past; and (2) a database of median price statistics at several geographic levels such as the zip code, city, and county where the subject property is situated. It is a significant advance to recognize how these methods can be combined and to devise an effective way of combining them to detect mortgage fraud with improved accuracy and efficiency. The method in accordance with the present invention astutely combines these two components to provide a number of advantages over existing fraud detection methods. For example, the method in accordance with the present invention can provide documentation if a lender is called upon to support a decision on a loan application. The efficiency of automated data processing reduces the cost of producing such documentation when it is called for.
- The scores and matrices produced by the method in accordance with the present invention can be requested and transmitted in an automated fashion for one property at a time or for thousands or millions of properties. The method can be used whenever needed, for subject properties and applications throughout the country. Thus, the method can achieve economies of scale.
- An entire bundle of loans may be analyzed pursuant to one request. The loans may be proposed loans, or they may be loans that were made in the past. Thus, the fraud sought to be detected may be prospective, or it may already have occurred. One may, therefore, use the present invention to re-evaluate the risk entailed in choices that were made in the past or that were made by others who, at the time, had a very different appreciation of the sensitivity and selectivity with which others later would evaluate the risk of fraud.
- The method in accordance with the present invention also embodies a recognition of the tactics and limitations of the perpetrators of mortgage fraud, with a view to making fraud much more difficult to accomplish and rendering fraudulent alleged values easier to detect. For example, perpetrators of fraud (“fraudsters”) are frequently able to arrange a series of real or alleged sales, appraisals, or loans for a subject property, often at ascending valuation levels, to support their claims of value for a sale or loan. Fraudsters also often arrange a series of real or alleged sales, appraisals, or loans for a set of properties in a single neighborhood, often at ascending valuation levels, to support their claims of ascending market valuations or prices, and to support their alleged valuation of a subject property for the purposes of a sale or loan.
- However, fraudsters will not have the resources to arrange enough false valuations or false sale prices to distort the overall price levels in a well-populated zip code, much less in an entire city or county, because there are many legitimate sales in such areas. Fraudsters also probably will not have the persistence to arrange a history of false valuations or prices on a subject property that extends several years into the past. In general, fraudsters are unlikely to spend three, five, or more years to build a trail of false valuations of a subject property. Combining a spatial distortion index with a temporal distortion index places the concealment of the attempted fraud beyond the resources and beyond the patience of fraudsters.
- Thus, an advantage of the method in accordance with the present invention is that it uses a combination of distortion ratio methods to differentiate realistic valuations, which are likely to result from underlying market phenomena, from various types of unrealistic valuations that are likely to result from the behaviors that fit the methods and motivations of fraudsters. The various advantages of the method combine to result in a substantial, novel, non-obvious advance over existing methods of detecting fraud in a mortgage application.
- The method in accordance with the present invention is also useful in identifying past transactions which gave rise to anomalous valuations. For example, one may wish to investigate the history of a particular property not only for indications of mortgage fraud, but also for indications that any party to a transaction recognized a value inconsistent with market conditions.
- For this purpose, a database of valuation-generating events is maintained in a computer system for a plurality of real properties in a geographic area in which the subject real property is located. A valuation-generating event may be a sale, a valuation pursuant to a mortgage application, or any other event indicating a value placed on the property by any party. A subject property record set including a price (or other valuation) of the property and the date thereof for at least one valuation-generating event is obtained from the computer. A valuation history data set for the subject property, comprising prices and the dates thereof for several timepoints, is obtained from the computer. This step may involve obtaining values generated by automated valuation models as well as values derived from other sources of data. Finally, historical sales data for property in the geographic area in which the subject real property is located is obtained from the computer. This data is obtainable, for example, from county recorders. To obtain suitable data, a database query may be formulated comprising such information as the location, type, and other economically important characteristics of the subject property, to the extent appropriate in light of the available data.
- In the manner described herein, price ratio data is computed using the valuation history for the subject property and the historical sales data for the subject property in the geographic area in which the subject property is located. Also in the manner described herein, a distortion index is computed based on the price ratio data to detect an anomalous valuation in the at least one valuation generating event.
- However, instead of computing and reporting a distortion index for a single property for the purpose of detecting fraud in a pending mortgage application, a distortion index is computed and displayed for each of a plurality of conditions so that patterns and relationships may be revealed. For example, for a single identified property the distortion index may be reported as a function of time. Alternatively, a particular timeframe may be selected and the distortion index may be reported as a function of other variables or combinations of variables. The variables may include, for example, the identity of the transferor or the transferee, the identity of the lender or loan officer, the geographical location, the municipal jurisdiction, or any other descriptive information associated with the property or with the transaction. It is possible, therefore, to associate certain individuals, brokers, lenders, environments or timeframes with certain valuation patterns that signal an anomalous valuation.
- Thus, the method in accordance with the present invention becomes a potent tool for risk management in secondary sales of financial instruments, as well as for historical and economic research and other investigative purposes.
- It will be appreciated that many variations are possible for practicing the invention without departing from the spirit of the present invention, whose scope is to be limited only by the claims appended to this specification.
Claims (20)
1. A method of detecting fraud during a real estate transaction, the method comprising:
using a computer processor to:
receive an estimated value of a subject real property;
access a database of spatial data, the spatial data comprising real estate prices in a geographic area in which the subject real property is located, the geographic area comprising at least one of the same zip code, city, or county as the subject real property;
generate a first spatial variance by computing ratios corresponding to the accessed real estate prices;
generate a second spatial variance by computing ratios corresponding to the accessed real estate prices; and
compute a spatial distortion based on the first spatial variance and the second spatial variance to indicate a likelihood of fraud.
2. The method of claim 1 , wherein the spatial data is generated by using sales data for properties in the geographic area.
3. The method of claim 1 , wherein the spatial data is generated by using an automated valuation model for properties in the geographic area.
4. The method of claim 1 , wherein the spatial data is generated by using a combination of sales data and an automated valuation model for properties in the geographic area.
5. The method of claim 1 , wherein the spatial data is generated from real estate prices from previous years.
6. The method of claim 1 , wherein the spatial data comprises property characteristics that are shared between the subject real property and properties in the geographic area.
7. The method of claim 1 , wherein one of the spatial variances comprise a ratio of the estimated value of the subject real property and a median real estate price of real property in the same zip code.
8. The method of claim 1 , wherein the spatial distortion comprises a difference between two years of spatial variances of the subject real property.
9. The method of claim 8 , wherein the two years comprise the current year and a previous year having the largest spatial variance.
10. A method of detecting fraud during a real estate transaction, the method comprising:
using a computer processor to:
receive an estimated value of a subject real property;
access a database of spatial data, the spatial data comprising real estate prices in a geographic area in which the subject real property is located, the geographic area comprising at least one of the same zip code, city, or county as the subject real property;
generate a set of spatial variances by computing ratios between a plurality of real estate prices of the subject real property and a plurality of real estate prices of properties in the geographic area;
compute a spatial distortion based on the set of spatial variances; and
produce a distortion ratio score to indicate a likelihood of fraud based on the spatial distortion.
11. The method of claim 10 , further comprising accessing a set of temporal data.
12. The method of claim 11 , further comprising generating a set of temporal variances, computing a temporal distortion based on the set of temporal variances, and computing a total distortion by adding the temporal distortion to the spatial distortion.
13. A system of detecting fraud during a real estate transaction, the method comprising:
a computer processor; and
a memory storing program instructions, said program instructions when executed by the computer processor causes the computer processor to:
receive an estimated value of a subject real property;
access a database of spatial data, the spatial data comprising real estate prices in a geographic area in which the subject real property is located, the geographic area comprising at least one of the same zip code, city, or county as the subject real property;
generate a set of spatial variances by computing ratios between a plurality of real estate prices of the subject real property and a plurality of real estate prices of properties in the geographic area;
compute a spatial distortion based on the set of spatial variances; and
produce a distortion ratio score to indicate a likelihood of fraud based on the spatial distortion.
14. The system of claim 13 , wherein the spatial data is generated by using a combination of sales data and an automated valuation model for properties in the geographic area.
15. The system of claim 13 , wherein the spatial data is generated from real estate prices from previous years.
16. The system of claim 13 , wherein the spatial data comprises property characteristics that are shared between the subject real property and properties in the geographic area.
17. The system of claim 13 , wherein one of the spatial variances comprise a ratio of the estimated value of the subject real property and a median real estate price of real property in the same zip code.
18. The system of claim 13 , wherein the spatial distortion comprises a difference between two years of spatial variances of the subject real property.
19. The system of claim 18 , wherein the two years comprise the current year and a previous year having the largest spatial variance.
20. A method of detecting fraud during a real estate transaction, the method comprising:
using a computer data processor to:
access a database of real property prices in a geographic area in which a subject real property is located;
using data from the database or data from a requestor to generate a temporal data set comprising a current yearly real property price for the subject real property and a set of past yearly real property prices for the subject real property;
generate from the database a spatial data set comprising a current yearly real property price for real property with similar characteristics as the subject real property and a set of past yearly real property prices for real property with similar characteristics as the subject real property;
generate a set of temporal variances;
generate a set of spatial variances;
compute a spatial distortion based on the set of spatial variances;
compute a temporal distortion based on the set of temporal variances; and
compute a total distortion by adding the temporal distortion to the spatial distortion.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US12/573,834 US20100088242A1 (en) | 2003-11-14 | 2009-10-05 | Method for mortgage fraud detection |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US10/713,348 US7599882B2 (en) | 2003-11-14 | 2003-11-14 | Method for mortgage fraud detection |
US12/573,834 US20100088242A1 (en) | 2003-11-14 | 2009-10-05 | Method for mortgage fraud detection |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/713,348 Continuation US7599882B2 (en) | 2003-11-14 | 2003-11-14 | Method for mortgage fraud detection |
Publications (1)
Publication Number | Publication Date |
---|---|
US20100088242A1 true US20100088242A1 (en) | 2010-04-08 |
Family
ID=34573693
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/713,348 Active 2027-08-22 US7599882B2 (en) | 2003-11-14 | 2003-11-14 | Method for mortgage fraud detection |
US12/573,834 Abandoned US20100088242A1 (en) | 2003-11-14 | 2009-10-05 | Method for mortgage fraud detection |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/713,348 Active 2027-08-22 US7599882B2 (en) | 2003-11-14 | 2003-11-14 | Method for mortgage fraud detection |
Country Status (1)
Country | Link |
---|---|
US (2) | US7599882B2 (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100106629A1 (en) * | 2006-06-13 | 2010-04-29 | First American Real Estate Tax Service, Llc. | Automatic delinquency item processing with customization for lenders |
US20120005112A1 (en) * | 2010-03-03 | 2012-01-05 | Bradley Woodworth | Submission validation system and method |
US8515863B1 (en) * | 2010-09-01 | 2013-08-20 | Federal Home Loan Mortgage Corporation | Systems and methods for measuring data quality over time |
US20130282596A1 (en) * | 2012-04-24 | 2013-10-24 | Corelogic Solutions, Llc | Systems and methods for evaluating property valuations |
Families Citing this family (41)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7369838B1 (en) * | 2000-10-03 | 2008-05-06 | At&T Corporation | Intra-premises wireless broadband service using lumped and distributed wireless radiation from cable source input |
US7599882B2 (en) * | 2003-11-14 | 2009-10-06 | First American Corelogic, Inc. | Method for mortgage fraud detection |
US20050171822A1 (en) * | 2004-02-03 | 2005-08-04 | First American Real Estate Solutions, L.P. | Responsive confidence scoring method for a proposed valuation of aproperty |
US20050187863A1 (en) * | 2004-02-20 | 2005-08-25 | Whinery Christopher S. | Method and system for protecting real estate from fraudulent transactions |
US7707103B2 (en) * | 2004-03-15 | 2010-04-27 | Arthur J Prieston | System and method for rating lenders |
US8311912B2 (en) * | 2004-03-15 | 2012-11-13 | Arthur J Prieston | Method for determining premiums for representation and warranty insurance for mortgage loans |
US7725386B2 (en) * | 2004-03-15 | 2010-05-25 | Arthur J Prieston | Method for offering representation and warranty insurance for mortgage loans |
US8055518B2 (en) * | 2004-03-15 | 2011-11-08 | Arthur J Prieston | Method for handling claims arising under representation and warranty insurance for mortgage loans |
US20050203779A1 (en) * | 2004-03-15 | 2005-09-15 | Prieston Arthur J. | Business structure for providing a representation and warranty insurance for mortgage loans |
US20060015357A1 (en) * | 2004-07-16 | 2006-01-19 | First American Real Estate Solutions, L.P. | Method and apparatus for spatiotemporal valuation of real estate |
US20060085234A1 (en) * | 2004-09-17 | 2006-04-20 | First American Real Estate Solutions, L.P. | Method and apparatus for constructing a forecast standard deviation for automated valuation modeling |
AU2005311862A1 (en) | 2004-11-30 | 2006-06-08 | Michael Dell Orfano | System and method for creating electronic real estate registration |
US9076185B2 (en) | 2004-11-30 | 2015-07-07 | Michael Dell Orfano | System and method for managing electronic real estate registry information |
US7853518B2 (en) * | 2005-05-24 | 2010-12-14 | Corelogic Information Solutions, Inc. | Method and apparatus for advanced mortgage diagnostic analytics |
US7809635B2 (en) | 2005-08-05 | 2010-10-05 | Corelogic Information Solutions, Inc. | Method and system for updating a loan portfolio with information on secondary liens |
US7668769B2 (en) * | 2005-10-04 | 2010-02-23 | Basepoint Analytics, LLC | System and method of detecting fraud |
US7587348B2 (en) * | 2006-03-24 | 2009-09-08 | Basepoint Analytics Llc | System and method of detecting mortgage related fraud |
US7966256B2 (en) | 2006-09-22 | 2011-06-21 | Corelogic Information Solutions, Inc. | Methods and systems of predicting mortgage payment risk |
US9031881B2 (en) * | 2006-06-30 | 2015-05-12 | Corelogic Solutions, Llc | Method and apparatus for validating an appraisal report and providing an appraisal score |
US7895127B2 (en) * | 2006-09-29 | 2011-02-22 | Weiser Anatoly S | Rating-based sorting and displaying of reviews |
US7546271B1 (en) * | 2007-12-20 | 2009-06-09 | Choicepoint Asset Company | Mortgage fraud detection systems and methods |
US7870049B1 (en) | 2008-08-15 | 2011-01-11 | United Services Automobile Association (Usaa) | Systems and methods for implementing real estate value insurance |
US7885879B1 (en) | 2008-08-15 | 2011-02-08 | United Services Automobile Association (Usaa) | Systems and methods for implementing real estate value insurance |
US7890403B1 (en) | 2008-08-15 | 2011-02-15 | United Services Automobile Association (Usaa) | Systems and methods for implementing real estate future market value insurance |
US7930447B2 (en) | 2008-10-17 | 2011-04-19 | International Business Machines Corporation | Listing windows of active applications of computing devices sharing a keyboard based upon requests for attention |
US10380652B1 (en) | 2008-10-18 | 2019-08-13 | Clearcapital.Com, Inc. | Method and system for providing a home data index model |
US8489499B2 (en) | 2010-01-13 | 2013-07-16 | Corelogic Solutions, Llc | System and method of detecting and assessing multiple types of risks related to mortgage lending |
US20110238566A1 (en) * | 2010-02-16 | 2011-09-29 | Digital Risk, Llc | System and methods for determining and reporting risk associated with financial instruments |
US8458074B2 (en) | 2010-04-30 | 2013-06-04 | Corelogic Solutions, Llc. | Data analytics models for loan treatment |
US10353761B2 (en) | 2011-04-29 | 2019-07-16 | Black Knight Ip Holding Company, Llc | Asynchronous sensors |
WO2013058846A1 (en) | 2011-10-18 | 2013-04-25 | Dotloop, Llc | Systems, methods and apparatus for form building |
US10826951B2 (en) | 2013-02-11 | 2020-11-03 | Dotloop, Llc | Electronic content sharing |
US9575622B1 (en) | 2013-04-02 | 2017-02-21 | Dotloop, Llc | Systems and methods for electronic signature |
US20150154664A1 (en) * | 2013-12-03 | 2015-06-04 | Fannie Mae | Automated reconciliation analysis model |
US20150154663A1 (en) * | 2013-12-03 | 2015-06-04 | Fannie Mae | Property appraisal discrepancy detection and assessment |
US10552525B1 (en) | 2014-02-12 | 2020-02-04 | Dotloop, Llc | Systems, methods and apparatuses for automated form templating |
US10733364B1 (en) | 2014-09-02 | 2020-08-04 | Dotloop, Llc | Simplified form interface system and method |
US11810001B1 (en) * | 2016-05-12 | 2023-11-07 | Federal Home Loan Mortgage Corporation (Freddie Mac) | Systems and methods for generating and implementing knowledge graphs for knowledge representation and analysis |
US20190266681A1 (en) * | 2018-02-28 | 2019-08-29 | Fannie Mae | Data processing system for generating and depicting characteristic information in updatable sub-markets |
US11681966B2 (en) | 2021-02-24 | 2023-06-20 | Fannie Mae | Systems and methods for enhanced risk identification based on textual analysis |
US11094135B1 (en) | 2021-03-05 | 2021-08-17 | Flyreel, Inc. | Automated measurement of interior spaces through guided modeling of dimensions |
Citations (50)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4870576A (en) * | 1986-03-19 | 1989-09-26 | Realpro, Ltd. | Real estate search and location system and method |
US4918526A (en) * | 1987-03-20 | 1990-04-17 | Digital Equipment Corporation | Apparatus and method for video signal image processing under control of a data processing system |
US5032989A (en) * | 1986-03-19 | 1991-07-16 | Realpro, Ltd. | Real estate search and location system and method |
US5193056A (en) * | 1991-03-11 | 1993-03-09 | Signature Financial Group Inc. | Data processing system for hub and spoke financial services configuration |
US5361201A (en) * | 1992-10-19 | 1994-11-01 | Hnc, Inc. | Real estate appraisal using predictive modeling |
US5414621A (en) * | 1992-03-06 | 1995-05-09 | Hough; John R. | System and method for computing a comparative value of real estate |
US5689305A (en) * | 1994-05-24 | 1997-11-18 | Kabushiki Kaisha Toshiba | System for deinterlacing digitally compressed video and method |
US5754850A (en) * | 1994-05-11 | 1998-05-19 | Realselect, Inc. | Real-estate method and apparatus for searching for homes in a search pool for exact and close matches according to primary and non-primary selection criteria |
US5794216A (en) * | 1995-07-14 | 1998-08-11 | Brown; Timothy Robert | Methods and system for data acquisition in a multimedia real estate database |
US5852810A (en) * | 1996-01-29 | 1998-12-22 | Student Housing Network | Geographic specific information search system and method |
US5857174A (en) * | 1997-11-21 | 1999-01-05 | Dugan; John W. | Real estate appraisal method and device for standardizing real property marketing analysis by using pre-adjusted appraised comparable sales |
US6115694A (en) * | 1995-08-25 | 2000-09-05 | General Electric Company | Method for validating specified prices on real property |
US6141648A (en) * | 1995-08-25 | 2000-10-31 | General Electric Company | Method for estimating the price per square foot value of real property |
US6178406B1 (en) * | 1995-08-25 | 2001-01-23 | General Electric Company | Method for estimating the value of real property |
US6323885B1 (en) * | 1998-09-18 | 2001-11-27 | Steven Paul Wiese | Real estate value map computer system |
US6397208B1 (en) * | 1999-01-19 | 2002-05-28 | Microsoft Corporation | System and method for locating real estate in the context of points-of-interest |
US6401070B1 (en) * | 1996-10-11 | 2002-06-04 | Freddie Mac | System and method for providing house price forecasts based on repeat sales model |
US6484176B1 (en) * | 1999-06-25 | 2002-11-19 | Baynet World, Inc. | System and process for providing remote interactive access to a real estate information database using a portable computing device |
US6505176B2 (en) * | 1998-06-12 | 2003-01-07 | First American Credit Management Solutions, Inc. | Workflow management system for an automated credit application system |
US6587841B1 (en) * | 1995-09-12 | 2003-07-01 | First American Credit Management Solutions, Inc. | Computer implemented automated credit application analysis and decision routing system |
US6609118B1 (en) * | 1999-06-21 | 2003-08-19 | General Electric Company | Methods and systems for automated property valuation |
US6636803B1 (en) * | 2001-11-30 | 2003-10-21 | Corus Home Realty | Real-estate information search and retrieval system |
US6681211B1 (en) * | 1998-04-24 | 2004-01-20 | Starmine Corporation | Security analyst estimates performance viewing system and method |
US6748369B2 (en) * | 1999-06-21 | 2004-06-08 | General Electric Company | Method and system for automated property valuation |
US20040128232A1 (en) * | 2002-09-04 | 2004-07-01 | Paul Descloux | Mortgage prepayment forecasting system |
US20040243450A1 (en) * | 2003-06-02 | 2004-12-02 | Bernard Thomas James | Method, system, and computer program product for real property metric monitoring |
US6836270B2 (en) * | 2001-07-10 | 2004-12-28 | Geojet Information Solutions, Inc. | 3-D map data visualization |
US6842738B1 (en) * | 1996-10-11 | 2005-01-11 | Freddie Mac | System and method for providing property value estimates |
US20050108025A1 (en) * | 2003-11-14 | 2005-05-19 | First American Real Estate Solutions, L.P. | Method for mortgage fraud detection |
US20050171822A1 (en) * | 2004-02-03 | 2005-08-04 | First American Real Estate Solutions, L.P. | Responsive confidence scoring method for a proposed valuation of aproperty |
US20050192999A1 (en) * | 2003-11-21 | 2005-09-01 | Cook Scott J. | System and method of virtualizing physical locations |
US20050216292A1 (en) * | 2003-10-11 | 2005-09-29 | Ashlock Jeffrey M | Method and system for financial evaluation of real estate properties |
US20050288942A1 (en) * | 2004-06-25 | 2005-12-29 | First American Real Estate Solutions, L.P. | Method and apparatus for valuing property |
US20060015357A1 (en) * | 2004-07-16 | 2006-01-19 | First American Real Estate Solutions, L.P. | Method and apparatus for spatiotemporal valuation of real estate |
US20060026136A1 (en) * | 2004-02-04 | 2006-02-02 | Realtydata Corp. | Method and system for generating a real estate title report |
US20060064415A1 (en) * | 2001-06-15 | 2006-03-23 | Isabelle Guyon | Data mining platform for bioinformatics and other knowledge discovery |
US20060085234A1 (en) * | 2004-09-17 | 2006-04-20 | First American Real Estate Solutions, L.P. | Method and apparatus for constructing a forecast standard deviation for automated valuation modeling |
US7043501B2 (en) * | 2001-12-21 | 2006-05-09 | Andrew Schiller | Method for analyzing demographic data |
US20060105342A1 (en) * | 2004-08-31 | 2006-05-18 | Mario Villena | Computerized systems for formation and update of databases |
US7054501B1 (en) * | 2000-11-14 | 2006-05-30 | Eastman Kodak Company | Estimating noise for a digital image utilizing updated statistics |
US20060122918A1 (en) * | 2004-12-08 | 2006-06-08 | Benjamin Graboske | Method and apparatus for testing automated valuation models |
US7076448B1 (en) * | 2000-09-12 | 2006-07-11 | Lettuce Marketing, Llc | Automated communication of neighborhood property value information for real estate marketing |
US20060200492A1 (en) * | 2004-08-31 | 2006-09-07 | Mario Villena | Automatic evaluation system using specialized communications interfaces |
US20060218003A1 (en) * | 2000-09-12 | 2006-09-28 | Snyder Steven L | Automated Communication of Neighborhood Property Value Information for Real Estate Marketing |
US20060218005A1 (en) * | 2004-08-31 | 2006-09-28 | Villena Jose A | Computerized agent and systems for automatic searching of properties having favorable attributes |
US20060271472A1 (en) * | 2005-05-24 | 2006-11-30 | First American Real Estate Solutions, L.P. | Method and apparatus for advanced mortgage diagnostic analytics |
US20070033122A1 (en) * | 2005-08-04 | 2007-02-08 | First American Real Estate Solutions, Lp | Method and apparatus for computing selection criteria for an automated valuation model |
US7289965B1 (en) * | 2001-08-10 | 2007-10-30 | Freddie Mac | Systems and methods for home value scoring |
US7333943B1 (en) * | 2000-08-11 | 2008-02-19 | The Prudential Insurance Company Of America | Method and system for managing real property transactions having internet access and control |
US20080097767A1 (en) * | 2000-04-27 | 2008-04-24 | Home Mart, Inc. | Method and System for Providing Real Estate Information Using a Computer Network, Such as the Internet |
Family Cites Families (32)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5680305A (en) | 1995-02-16 | 1997-10-21 | Apgar, Iv; Mahlon | System and method for evaluating real estate |
US5867155A (en) | 1996-03-18 | 1999-02-02 | Williams; Douglas | Large scale distributive video on demand system for the distribution of real estate properties information |
US6249775B1 (en) * | 1997-07-11 | 2001-06-19 | The Chase Manhattan Bank | Method for mortgage and closed end loan portfolio management |
US7110970B2 (en) | 1999-12-30 | 2006-09-19 | Ge Capital Commercial Finance, Inc. | Methods and apparatus for rapid deployment of a valuation system |
JP2001236369A (en) | 2000-02-23 | 2001-08-31 | Koncheruto:Kk | System for map information with longitude and latitude |
US20010039506A1 (en) | 2000-04-04 | 2001-11-08 | Robbins Michael L. | Process for automated real estate valuation |
US20010047327A1 (en) | 2000-04-10 | 2001-11-29 | Courtney Michael T. | System and method for calculating mortgage loan balance to appraisal value ratio |
KR20010105569A (en) | 2000-05-16 | 2001-11-29 | 전정철 | 3- Dimensional real-estate geographic Information internet service system and method thereof |
KR20020004710A (en) | 2000-07-07 | 2002-01-16 | 권오억 | A method for displaying a real estate price-related information using internet and using geographical information system or internet geographical information system, and a method for caculating real estate price using a map or a land registration map in geogrphical information system and displaying it through internet home page |
US7974930B2 (en) | 2000-07-26 | 2011-07-05 | Pierce-Eislen, Inc. | Method and system for providing real estate information |
JP2002123589A (en) | 2000-10-13 | 2002-04-26 | Dainippon Printing Co Ltd | Method and device for providing information and real estate information providing system |
CA2326055A1 (en) * | 2000-11-15 | 2002-05-15 | Reavs Information Technologies Limited | Method and system for automated decisioning in financial lending processes |
CA2332255A1 (en) * | 2001-01-24 | 2002-07-24 | James A. Cole | Automated mortgage fraud detection system and method |
US20020103669A1 (en) | 2001-01-29 | 2002-08-01 | Sullivan Thomas W. | Methods and systems for coordinating the flow of data |
US20020147613A1 (en) | 2001-04-10 | 2002-10-10 | Kennard Robert M. | Methods of marketing summary maps depicting the location of real property and certain traits in the vicinity thereof |
KR20010078857A (en) | 2001-04-28 | 2001-08-22 | 이도훈 | Real Estate Agent Management System which is applied to Real Estate Offerings Management Method based on GIS |
US7054741B2 (en) | 2002-02-11 | 2006-05-30 | Landnet Corporation | Land software tool |
US7366694B2 (en) | 2001-08-16 | 2008-04-29 | Mortgage Grader, Inc. | Credit/financing process |
US7680728B2 (en) | 2001-08-16 | 2010-03-16 | Mortgage Grader, Inc. | Credit/financing process |
US7219078B2 (en) | 2001-09-06 | 2007-05-15 | Causeway Data Communications Limited | Spatially-based valuation of property |
US20040021584A1 (en) | 2001-11-30 | 2004-02-05 | Hartz Daniel K. | Market status icons in real-estate information search and retrieval system |
US7454383B2 (en) | 2001-12-31 | 2008-11-18 | Ge Corporate Financial Services, Inc. | Methods and systems for assessing loan portfolios |
US7587361B2 (en) | 2002-01-31 | 2009-09-08 | Ge Mortgage Holdings, Llc | Methods and apparatus for electronic reporting of mortgage delinquency |
US7630932B2 (en) | 2002-01-31 | 2009-12-08 | Transunion Interactive, Inc. | Loan rate and lending information analysis system |
US20030149658A1 (en) | 2002-02-06 | 2003-08-07 | Radian Group, Inc. | System for providing a warranty for the automated valuation of property |
US20030191723A1 (en) * | 2002-03-28 | 2003-10-09 | Foretich James Christopher | System and method for valuing real property |
US20040019517A1 (en) | 2002-07-26 | 2004-01-29 | Fidelity National Information Solutions, Inc. | Method of establishing an insurable value estimate for a real estate property |
US7680673B2 (en) | 2002-08-23 | 2010-03-16 | Wheeler Cynthia R | System for real estate sale management |
US20040049440A1 (en) | 2002-09-11 | 2004-03-11 | Masahiro Shinoda | Real estate appraisal auxiliary system, a storage medium with a computer software program stored therein for use by a computer system to assist in appraising real estate, and a real estate appraisal auxiliary method |
US20040133493A1 (en) | 2002-11-04 | 2004-07-08 | Ford Timothy K. | Method and system for comprehensive real estate transaction management |
KR20050064605A (en) | 2003-12-24 | 2005-06-29 | 아이디어플라자(주) | Geographical information display apparatus of real-estates and display method thereof |
US7809635B2 (en) | 2005-08-05 | 2010-10-05 | Corelogic Information Solutions, Inc. | Method and system for updating a loan portfolio with information on secondary liens |
-
2003
- 2003-11-14 US US10/713,348 patent/US7599882B2/en active Active
-
2009
- 2009-10-05 US US12/573,834 patent/US20100088242A1/en not_active Abandoned
Patent Citations (50)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5032989A (en) * | 1986-03-19 | 1991-07-16 | Realpro, Ltd. | Real estate search and location system and method |
US4870576A (en) * | 1986-03-19 | 1989-09-26 | Realpro, Ltd. | Real estate search and location system and method |
US4918526A (en) * | 1987-03-20 | 1990-04-17 | Digital Equipment Corporation | Apparatus and method for video signal image processing under control of a data processing system |
US5193056A (en) * | 1991-03-11 | 1993-03-09 | Signature Financial Group Inc. | Data processing system for hub and spoke financial services configuration |
US5414621A (en) * | 1992-03-06 | 1995-05-09 | Hough; John R. | System and method for computing a comparative value of real estate |
US5361201A (en) * | 1992-10-19 | 1994-11-01 | Hnc, Inc. | Real estate appraisal using predictive modeling |
US5754850A (en) * | 1994-05-11 | 1998-05-19 | Realselect, Inc. | Real-estate method and apparatus for searching for homes in a search pool for exact and close matches according to primary and non-primary selection criteria |
US5689305A (en) * | 1994-05-24 | 1997-11-18 | Kabushiki Kaisha Toshiba | System for deinterlacing digitally compressed video and method |
US5794216A (en) * | 1995-07-14 | 1998-08-11 | Brown; Timothy Robert | Methods and system for data acquisition in a multimedia real estate database |
US6115694A (en) * | 1995-08-25 | 2000-09-05 | General Electric Company | Method for validating specified prices on real property |
US6141648A (en) * | 1995-08-25 | 2000-10-31 | General Electric Company | Method for estimating the price per square foot value of real property |
US6178406B1 (en) * | 1995-08-25 | 2001-01-23 | General Electric Company | Method for estimating the value of real property |
US6587841B1 (en) * | 1995-09-12 | 2003-07-01 | First American Credit Management Solutions, Inc. | Computer implemented automated credit application analysis and decision routing system |
US5852810A (en) * | 1996-01-29 | 1998-12-22 | Student Housing Network | Geographic specific information search system and method |
US6401070B1 (en) * | 1996-10-11 | 2002-06-04 | Freddie Mac | System and method for providing house price forecasts based on repeat sales model |
US6842738B1 (en) * | 1996-10-11 | 2005-01-11 | Freddie Mac | System and method for providing property value estimates |
US5857174A (en) * | 1997-11-21 | 1999-01-05 | Dugan; John W. | Real estate appraisal method and device for standardizing real property marketing analysis by using pre-adjusted appraised comparable sales |
US6681211B1 (en) * | 1998-04-24 | 2004-01-20 | Starmine Corporation | Security analyst estimates performance viewing system and method |
US6505176B2 (en) * | 1998-06-12 | 2003-01-07 | First American Credit Management Solutions, Inc. | Workflow management system for an automated credit application system |
US6323885B1 (en) * | 1998-09-18 | 2001-11-27 | Steven Paul Wiese | Real estate value map computer system |
US6397208B1 (en) * | 1999-01-19 | 2002-05-28 | Microsoft Corporation | System and method for locating real estate in the context of points-of-interest |
US6609118B1 (en) * | 1999-06-21 | 2003-08-19 | General Electric Company | Methods and systems for automated property valuation |
US6748369B2 (en) * | 1999-06-21 | 2004-06-08 | General Electric Company | Method and system for automated property valuation |
US6484176B1 (en) * | 1999-06-25 | 2002-11-19 | Baynet World, Inc. | System and process for providing remote interactive access to a real estate information database using a portable computing device |
US20080097767A1 (en) * | 2000-04-27 | 2008-04-24 | Home Mart, Inc. | Method and System for Providing Real Estate Information Using a Computer Network, Such as the Internet |
US7333943B1 (en) * | 2000-08-11 | 2008-02-19 | The Prudential Insurance Company Of America | Method and system for managing real property transactions having internet access and control |
US20060218003A1 (en) * | 2000-09-12 | 2006-09-28 | Snyder Steven L | Automated Communication of Neighborhood Property Value Information for Real Estate Marketing |
US7076448B1 (en) * | 2000-09-12 | 2006-07-11 | Lettuce Marketing, Llc | Automated communication of neighborhood property value information for real estate marketing |
US7054501B1 (en) * | 2000-11-14 | 2006-05-30 | Eastman Kodak Company | Estimating noise for a digital image utilizing updated statistics |
US20060064415A1 (en) * | 2001-06-15 | 2006-03-23 | Isabelle Guyon | Data mining platform for bioinformatics and other knowledge discovery |
US6836270B2 (en) * | 2001-07-10 | 2004-12-28 | Geojet Information Solutions, Inc. | 3-D map data visualization |
US7289965B1 (en) * | 2001-08-10 | 2007-10-30 | Freddie Mac | Systems and methods for home value scoring |
US6636803B1 (en) * | 2001-11-30 | 2003-10-21 | Corus Home Realty | Real-estate information search and retrieval system |
US7043501B2 (en) * | 2001-12-21 | 2006-05-09 | Andrew Schiller | Method for analyzing demographic data |
US20040128232A1 (en) * | 2002-09-04 | 2004-07-01 | Paul Descloux | Mortgage prepayment forecasting system |
US20040243450A1 (en) * | 2003-06-02 | 2004-12-02 | Bernard Thomas James | Method, system, and computer program product for real property metric monitoring |
US20050216292A1 (en) * | 2003-10-11 | 2005-09-29 | Ashlock Jeffrey M | Method and system for financial evaluation of real estate properties |
US20050108025A1 (en) * | 2003-11-14 | 2005-05-19 | First American Real Estate Solutions, L.P. | Method for mortgage fraud detection |
US20050192999A1 (en) * | 2003-11-21 | 2005-09-01 | Cook Scott J. | System and method of virtualizing physical locations |
US20050171822A1 (en) * | 2004-02-03 | 2005-08-04 | First American Real Estate Solutions, L.P. | Responsive confidence scoring method for a proposed valuation of aproperty |
US20060026136A1 (en) * | 2004-02-04 | 2006-02-02 | Realtydata Corp. | Method and system for generating a real estate title report |
US20050288942A1 (en) * | 2004-06-25 | 2005-12-29 | First American Real Estate Solutions, L.P. | Method and apparatus for valuing property |
US20060015357A1 (en) * | 2004-07-16 | 2006-01-19 | First American Real Estate Solutions, L.P. | Method and apparatus for spatiotemporal valuation of real estate |
US20060200492A1 (en) * | 2004-08-31 | 2006-09-07 | Mario Villena | Automatic evaluation system using specialized communications interfaces |
US20060218005A1 (en) * | 2004-08-31 | 2006-09-28 | Villena Jose A | Computerized agent and systems for automatic searching of properties having favorable attributes |
US20060105342A1 (en) * | 2004-08-31 | 2006-05-18 | Mario Villena | Computerized systems for formation and update of databases |
US20060085234A1 (en) * | 2004-09-17 | 2006-04-20 | First American Real Estate Solutions, L.P. | Method and apparatus for constructing a forecast standard deviation for automated valuation modeling |
US20060122918A1 (en) * | 2004-12-08 | 2006-06-08 | Benjamin Graboske | Method and apparatus for testing automated valuation models |
US20060271472A1 (en) * | 2005-05-24 | 2006-11-30 | First American Real Estate Solutions, L.P. | Method and apparatus for advanced mortgage diagnostic analytics |
US20070033122A1 (en) * | 2005-08-04 | 2007-02-08 | First American Real Estate Solutions, Lp | Method and apparatus for computing selection criteria for an automated valuation model |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100106629A1 (en) * | 2006-06-13 | 2010-04-29 | First American Real Estate Tax Service, Llc. | Automatic delinquency item processing with customization for lenders |
US8224745B2 (en) | 2006-06-13 | 2012-07-17 | Corelogic Tax Services, Llc | Automatic delinquency item processing with customization for lenders |
US20120005112A1 (en) * | 2010-03-03 | 2012-01-05 | Bradley Woodworth | Submission validation system and method |
US8515863B1 (en) * | 2010-09-01 | 2013-08-20 | Federal Home Loan Mortgage Corporation | Systems and methods for measuring data quality over time |
US9747639B1 (en) | 2010-09-01 | 2017-08-29 | Federal Home Loan Mortgage Corporation (Freddie Mac) | Systems and methods for measuring data quality over time |
US11017467B1 (en) | 2010-09-01 | 2021-05-25 | Federal Home Loan Mortgage Corporation (Freddie Mac) | Systems and methods for measuring data quality over time |
US11556983B1 (en) | 2010-09-01 | 2023-01-17 | Federal Home Loan Mortgage Corporation (Freddie Mac) | Systems and methods for measuring data quality over time |
US12039597B1 (en) | 2010-09-01 | 2024-07-16 | Federal Home Loan Mortgage Corporation (Freddie Mac) | Systems and methods for measuring data quality over time |
US20130282596A1 (en) * | 2012-04-24 | 2013-10-24 | Corelogic Solutions, Llc | Systems and methods for evaluating property valuations |
Also Published As
Publication number | Publication date |
---|---|
US7599882B2 (en) | 2009-10-06 |
US20050108025A1 (en) | 2005-05-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7599882B2 (en) | Method for mortgage fraud detection | |
Bhutta et al. | Consumer ruthlessness and mortgage default during the 2007 to 2009 housing bust | |
US11798076B1 (en) | Systems and methods for adjusting the value of distressed properties | |
Harrison et al. | Environmental determinants of housing prices: The impact of flood zone status | |
US7546271B1 (en) | Mortgage fraud detection systems and methods | |
US7451095B1 (en) | Systems and methods for income scoring | |
US8458062B2 (en) | Real-time product matching | |
US20050171822A1 (en) | Responsive confidence scoring method for a proposed valuation of aproperty | |
Kaplan et al. | An analysis of the relationship between housing foreclosures, lending practices, and neighborhood ecology: Evidence from a distressed county | |
US8628151B1 (en) | Systems and methods for facilitating financial transactions involving bundles of properties | |
US20070294163A1 (en) | System and method for retaining mortgage customers | |
WO2007149941A2 (en) | System and method for acquiring mortgage customers | |
AU2014203430A1 (en) | Systems and methods for microfinance credit data processing and reporting | |
AU2011221385A1 (en) | Automated mining and processing of data associated with real estate | |
US7693764B1 (en) | Systems and methods for assessing property value fraud | |
US20160071207A1 (en) | Method for weighting a credit score and display of business score | |
Josephson et al. | The demand for post‐Katrina disaster aid: SBA disaster loans and small businesses in Mississippi | |
Frimpong et al. | Measuring heterogeneous price effects for home acquisition programs in at‐risk regions | |
Batinti et al. | Do economic recessions “squeeze the middle class”? | |
Huang et al. | The impact of default and foreclosure on housing values: Rings vs. neighborhoods approach | |
US20170098280A1 (en) | Systems and methods for detecting fraud in subscriber enrollment | |
Fraenkel | Property Tax-Induced Mobility and Redistribution | |
Lyons et al. | A profile of nontraditional agricultural real estate lender activity in the secondary market | |
Kelly | Appraisals, automated valuation models, and mortgage default | |
Li et al. | A new mortgage credit availability index |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |