WO2020206497A1

WO2020206497A1 - Peer deposit method and system

Info

Publication number: WO2020206497A1
Application number: PCT/AU2020/050352
Authority: WO
Inventors: Ian Christopher BAKER
Original assignee: Ge Mini D Pty Ltd
Priority date: 2019-04-10
Filing date: 2020-04-09
Publication date: 2020-10-15
Also published as: AU2020256912A1

Abstract

A computational method for obtaining a deposit is provided. The method includes steps of matching a plurality of lender profiles corresponding to respective lenders with a deposit loan profile corresponding to a borrower; connecting the plurality of lenders to the deposit loan profile; and obtaining deposit loan offers for the deposit loan profile from the plurality of lenders. The matching of the plurality of lender profiles to the deposit loan profile may be performed using a machine learning model. An associated computer system is also provided.

Description

PEER DEPOSIT METHOD AND SYSTEM

[0001 ] This invention relates to a computational process and system for facilitating access to a loan deposit. More particularly, the invention relates to computational peer-based lending to provide a borrower with a loan deposit and offset the need for lenders insurance, although without limitation thereto.

BACKGROUND

[0002] Lenders insurance refers generally to an insurance policy purchased by a lender, such as a bank, and paid for by a borrower, which can be required by a lender where the borrower seeks a loan in the absence of a deposit or downpayment considered sufficient. In general terms, the purpose of lenders insurance is to protect a lender where a borrower defaults on a secured loan, and sale of an asset securing the loan fails to recoup the balance of the loan.

[0003] A common form of lenders insurance is Lenders Mortgage Insurance (LMI), also referred variously to as, e.g., low equity premium, equalisation fee, and reduced equity fee, and typically associated with real estate loans, e.g. home loans. LMI typically takes the form of a relatively expensive, single-use policy, non-transferable between lending institutions, and not subject to negotiation or cancellation by a borrower. Generally, where the loan is paid out, most of the LMI premium is not refunded to the borrower. Additionally, LMI is normally incorporated into an overall loan, which results in the borrower paying interest for the full term of the loan.

[0004] Strategies enabling a borrower to obtain a loan without the need for LMI are frequently desirable. In some cases, it may be possible for a borrower to obtain a loan without the need for LMI if a guarantor for the loan can be identified. For example, in the context of real estate loans, a family member {e.g. parent) may act as guarantor to obviate the need for LMI such as in a ‘family pledge’ or ‘family guarantee’ arrangement. However, in many cases, a suitable guarantor is not available.

[0005] New computational approaches enabling efficient provision to a borrower, under appropriate circumstances, of a sufficient deposit or downpayment to obviate the need for LMI, would be desirable. In at least some circumstances, it would be highly desirable to match characteristics of a borrower with characteristics of potential deposit loan providers, for the purpose of providing a deposit loan to the borrower. [0006] Reference to prior art in the background is not and should not be taken as an acknowledgement or any form of suggestion that the referenced prior art forms part of the common general knowledge in the technical field of the present invention.

SUMMARY

[0007] A first aspect of the invention broadly provides a computational method of obtaining a deposit, including steps of:

connecting a deposit loan profile to a plurality of lenders; and

obtaining respective deposit loan offers for the deposit loan profile from each of the plurality of lenders,

to thereby obtain the deposit.

[0008] Suitably, the deposit loan profile corresponds to or is otherwise associated with a borrower for or on behalf of whom the deposit is obtained.

[0009] In embodiments, the step of connecting the deposit loan profile to a plurality of lenders includes sharing a data link with the plurality of lenders. In embodiments, the data link is an internet link. In embodiments, the link is a URL link. In embodiments, connection of the plurality of lenders to the deposit loan profile via the data link is secured.

[0010] Suitably, the respective deposit loan offers for the deposit loan profile obtained from the plurality of lenders are obtained subject to one or more conditions. In embodiments, the one or more conditions include a condition selected from deposit loan amount, deposit loan term, deposit loan repayment frequency, and deposit loan interest rate.

[001 1 ] In embodiments, one or more conditions subject to which the respective deposit loan offers are obtained from the plurality of lenders are the same. In embodiments, one or more conditions subject to which the respective deposit loan offers are obtained from the plurality of lenders are different. In embodiments wherein the one or more conditions are different, suitably, the respective deposit loan offers are competitive deposit loan offers.

[0012] The respective deposit loan offers obtained from the plurality of lenders for the deposit loan profile may be indexed to the deposit loan profile according to the method of this aspect. [0013] The method of this aspect may include a further step of creating the deposit loan profile, prior to the step of connecting the deposit loan profile to the plurality of lenders.

[0014] In embodiments, the step of creating the deposit loan profile includes indexing data for the required deposit to the deposit loan profile.

[0015] In embodiments, the step of creating the deposit loan profile includes indexing borrower data selected from personal data, social data, income data, asset data, expenditure data, current borrowing data, and previous borrowing data to the deposit loan profile.

[0016] The step of creating the deposit loan profile may include indexing data selected from primary loan data, desired deposit loan data, and preferred or desirable lender data to the deposit loan profile.

[0017] In embodiments, the step of creating the deposit loan profile includes indexing data obtained by or using a machine learning model to the deposit loan profile. In embodiments, the data obtained by or using a machine learning model is preferred or desirable lender data.

[0018] The method of this aspect may include a further step of assessing the deposit loan profile. In embodiments, the step of assessing the deposit loan profile is performed prior to the step of connecting the deposit loan profile to a plurality of lenders. Suitably, the step of assessing the deposit loan profile uses information indexed to the deposit loan profile.

[0019] In embodiments, the step of assessing the deposit loan profile includes calculating a risk rating for the deposit loan profile. In embodiments, the risk rating is a categorical risk rating. In embodiments, the risk rating is a numerical risk rating. The risk rating may be indexed to the deposit loan profile according to the method of this aspect.

[0020] In embodiments, the step of assessing the deposit loan profile includes approving or denying the deposit loan profile. In embodiments, approving or denying the deposit loan profile is performed using a risk rating calculated for the deposit loan profile. Approval or denial of the deposit loan profile may be indexed to the deposit loan profile according to the method of this aspect.

[0021 ] In embodiments, the deposit loan profile is approved subject to a condition. In embodiments, the deposit loan profile is approved subject to a condition selected from deposit loan amount, deposit loan term, deposit loan repayment frequency, and deposit loan interest rate. In embodiments, the condition is determined using a risk rating calculated for the deposit loan profile. A condition subject to which the deposit loan profile is approved may be indexed to the deposit loan profile according to the method of this aspect.

[0022] In embodiments, the step of assessing the deposit loan profile comprises, consists essentially of, or consists of assessing the deposit loan profile by or using a machine learning model.

[0023] In embodiments, the step of approving or denying the deposit loan profile comprises, consists essentially of, or consists of approving or denying the deposit loan profile by or using a machine learning model.

[0024] In embodiments, the step of approving the deposit loan profile subject to a condition comprises, consists essentially of, or consists of approving the deposit loan profile subject to a condition determined by or using a machine learning model.

[0025] The method of this aspect may include a further step of matching each of the plurality of lenders with the deposit loan profile, prior to connecting the deposit loan profile to the lender.

[0026] Suitably, the step of matching the lender with the deposit loan profile includes matching a lender profile of, corresponding to, or associated with the lender, with the deposit loan profile.

[0027] In embodiments, the step of matching the lender with the deposit loan profile comprises, consists essentially of, or consists of matching the lender to the deposit loan profile by or using a machine learning model.

[0028] The method of this aspect may include a further step of comparing a plurality of potential lenders to the deposit loan profile prior to matching each of the plurality of lenders with the deposit loan profile.

[0029] Suitably, the step of comparing the potential lender to the deposit loan profile includes comparing a potential lender profile of the potential lender to the deposit loan profile.

[0030] In embodiments, the step of comparing the potential lender to the deposit loan profile comprises, consists essentially of, or consists of comparing the potential lender to the deposit loan profile by or using a machine learning model. [0031 ] The method of this aspect may include a further step of creating one or more lender profiles for the respective lenders and/or creating one or more potential lender profiles for the respective potential lenders.

[0032] In embodiments, the step of creating the lender profile or the potential lender profile includes indexing lender or potential lender data selected from personal data, social data, income data, asset data, expenditure data, current lending data, and previous lending data to the lender profile or the potential lender profile.

[0033] The step of creating the lender profile or the potential lender profile may include indexing data selected from preferred or desirable primary loan data, preferred or desirable deposit loan data, and preferred or desirable borrower data to the potential lender profile or the lender profile.

[0034] In embodiments, the step of creating the lender profile or the potential lender profile includes indexing data obtained using a machine learning model to the lender profile or the potential lender profile. In embodiments, the data obtained using a machine learning model is preferred or desirable borrower data.

[0035] The method of this aspect may include a further step of evaluating a deposit loan offer for the deposit loan profile obtained from the plurality of lenders.

[0036] In embodiments, the step of evaluating the deposit loan offer includes comparing a condition obtained for the deposit loan offer to a condition subject to which the deposit loan profile is approved.

[0037] In embodiments, the step of evaluating the deposit loan offer includes a step of prioritising the deposit loan offer relative to other deposit loan offers.

[0038] In embodiments, the deposit loan offers are prioritised based on a condition subject to which the deposit loan offers are obtained.

[0039] In embodiments, the deposit loan offers are prioritised based on comparison of the respective lender with the deposit loan profile. Suitably, comparison of the respective lender with the deposit loan profile is or includes comparison of a lender profile of, corresponding to, or associated with the respective lender with the deposit loan profile.

[0040] In embodiments, the step of evaluating the deposit loan offer comprises, consists essentially of, or consists of evaluating the deposit loan offer by or using a machine learning model. [0041 ] In embodiments, the step of evaluating the deposit loan offer includes obtaining a decision on the deposit loan offer from a borrower.

[0042] Evaluation of a deposit loan offer for the deposit loan profile obtained from the plurality of lenders may be indexed to the deposit loan profile according to the method of this aspect.

[0043] The method of this aspect may include a further step of obtaining a repayment for the deposit. The repayment for the deposit may be indexed to the deposit loan profile according to the method of this aspect.

[0044] The method of this aspect may include a further step of valuing and/or assessing equity of an asset corresponding to or associated with the deposit. The value and/or equity of the asset corresponding to or associated with the deposit may be indexed to the deposit loan profile according to the method of this aspect.

[0045] In embodiments, the step of valuing and/or assessing equity of an asset associated with the deposit comprises, consists essentially of, or consists of valuing and/or assessing equity of the asset by or using a machine learning model.

[0046] The method of this aspect may include a further step of transferring the deposit from a first primary loan to a second primary loan via the deposit loan profile. Transfer of the deposit according to embodiments of this aspect may be indexed to the deposit loan profile.

[0047] In a second aspect, there is provided a computing system comprising a processor; and a transmitter and a receiver connected to the processor, the computer system being adapted to connect a deposit loan profile to a plurality of lenders; and obtain respective deposit loan offers for the deposit loan profile from each of the plurality of lenders.

[0048] The computing system of this aspect may further be adapted to create the deposit loan profile.

[0049] The processor of the computing system may further be adapted to assess the deposit loan profile.

[0050] In embodiments, the computing system of this aspect is adapted to create one or more lender profiles.

[0051 ] In embodiments, the computing system of this aspect is adapted to create one or more potential lender profiles. [0052] In embodiments, the processor of the computing system is adapted to run one or more machine learning models. In embodiments, the processor of the computing system is adapted to update one or more machine learning models. In embodiments, the processor of the computing system is adapted to produce one or more machine learning models.

[0053] In embodiments, the processor is adapted to compare one or more lender profiles or potential lender profiles with the deposit loan profile. Suitably, the processor is adapted to compare one or more lender profiles or potential lender profiles by or using a machine learning model.

[0054] In embodiments, the processor is adapted to prioritise the plurality of deposit loan offers for the deposit loan profile. Suitably, the processor is adapted to prioritise the plurality of deposit loan offers for the deposit loan profile by or using a machine learning model.

[0055] In embodiments, the transmitter and/or receiver comprise an internet connection.

[0056] In embodiments, the computing system comprises an input component connected to the processor. The input component will be adapted for inputting data, such as data to be indexed to the deposit loan profile.

[0057] In embodiments, the computing system comprises a storage component connected to the processor. The storage component will be adapted for storage of data, such as data indexed to the deposit loan profile.

[0058] Suitably, the computing system may further comprise a power source. The power source may be any suitable power source inclusive of batteries such as lithium ion batteries, and AC or DC power sources.

[0059] In embodiments, the computing system of the second aspect is for, suitable for, or when used for the method of the first aspect.

[0060] An alternative aspect of the present invention provides a computational method of obtaining a loan, including steps of:

connecting a loan profile to a plurality of lenders; and

obtaining respective loan offers for the loan profile from each of the plurality of lenders,

to thereby obtain the loan. [0061 ] In embodiments, the method of this alternative aspect is substantially as described for the first aspect, with the exception that the deposit loan profile is instead any suitable loan profile; the deposit loan offer is instead any suitable loan offer; and the deposit is instead any suitable loan.

[0062] As used in this specification, the indefinite articles“a” and“an” are not to be read as singular indefinite articles or as otherwise excluding more than one or more than a single subject to which the indefinite article refers. For example,“a” machine learning model includes one machine learning model, one or more machine learning models, and a plurality of machine learning models.

[0063] As used in this specification, the terms“comprises",“comprising”,“includes", “including”,“contains”, and“containing, and similar terms, are intended to mean a non-exclusive inclusion, such that a method or system that comprises, includes, or contains a list of elements, components, or steps does not necessarily possess those elements, components, or steps solely, but may well possess other elements, components, or steps not listed.

[0064] In this specification, the terms “consisting essentially of and “consists essentially of are intended to mean a non-exclusive inclusion only to the extent that, if additional elements are included beyond those elements recited, the additional elements do not materially alter basic and novel characteristics. That is, an apparatus, system, or method that“consists essentially of one or more recited elements includes those elements only, or those elements and any additional elements that do not materially alter the basic and novel characteristics of the apparatus, system, or method.

BRIEF DESCRIPTION OF THE DRAWINGS

[0065] The invention will be described hereinafter with reference to exemplary embodiments illustrated in the drawings, wherein:

[0066] Figure 1 sets forth a schematic of a typical method as described herein, method 1 , and its interaction with a borrower, borrower 2, and a plurality of lenders, lenders 3.

[0067] Figure 2 sets forth a schematic of certain optional steps according to embodiments of method 1.

[0068] Figure 3 sets forth a schematic of certain optional steps according to embodiments of method 1. [0069] Figure 4 sets forth schematics (4A and 4B) illustrating implementations of method 1.

[0070] Figure 5 sets forth a schematic illustrating an implementation of method 1 , in the context of purchase of a home.

[0071 ] Figure 6 sets forth a schematic illustrating an implementation of method 1 , in the context of purchasing real estate.

[0072] Figure 7 sets forth a schematic based on Figure 6, wherein a deposit associated with a first property is transferred to a second property using method 1.

[0073] Figure 8 sets forth a schematic based on Figure 6, wherein a deposit for a refinanced property is obtained using method 1.

[0074] Figure 9 sets forth a schematic of an embodiment of a system of the invention, system 1000.

DESCRIPTION OF EMBODIMENTS

[0075] The invention as described herein is at least partly predicated on the realisation that there is a need for alternatives to lenders insurance. Accordingly, the invention broadly provides a computational or computer-implemented method for obtaining a deposit. A computer system adapted to obtain a deposit is also broadly provided.

[0076] Some embodiments of the invention are at least partly predicated on the realisation that there is scope to apply machine learning to achieve benefits or advantages in a lending context. For example, it has been realised that the application of machine learning in the context of obtaining a deposit may have benefits in respect of efficiency and/or desirable outcomes for borrowers and/or lenders.

[0077] Some embodiments of the invention are at least partly predicated on the realisation that there is scope to compare data for borrowers and/or lenders to achieve benefits or advantages in a lending context. For example, it has been realised that comparing social or demographic data for a borrower seeking a deposit loan and/or lenders offering deposit loans may have benefits in appropriately matching borrowers with lenders.

[0078] Some embodiments of the invention are at least partly predicated on the realisation that there is scope to assess publicly available data for borrowers and/or lenders to achieve benefits or advantages in a lending context. For example, it has been realised that obtaining publicly available data for a borrower seeking a deposit loan and/or lenders offering deposit loans may have benefits in appropriately matching borrowers with lenders.

[0079] As used herein, a“computational’ or“computer-implemented’ method will be understood to be a method wherein at least part of the method is performed using a computer or computing system. In some embodiments, all, or substantially all, of the method is performed using a computer or computing system.

[0080] As used herein,“machine learning” will be understood to refer to algorithms and models, such as statistical models, that are used by computer systems to perform tasks in the absence of specific user instructions. Typically, machine learning models rely on pattern recognition and inference, although without limitation thereto.

[0081 ] It will be understood by the skilled person that machine learning algorithms can include supervised learning algorithms, unsupervised learning algorithms, semi- supervised learning algorithms, reinforcement learning algorithms, self-learning algorithms, feature learning algorithms, anomaly detection algorithms, and association rules algorithms.

[0082] It will further be understood by the skilled person that machine learning models include artificial neural network models, decision tree models, support vector machine models, regressions analysis models, Bayesian network models, and genetic models.

[0083] More generally, machine learning approaches can be broadly classified as supervised learning approaches, unsupervised learning approaches, and reinforcement learning approaches.

[0084] To avoid doubt, a“machine learning modef’ as used herein includes and encompasses models developed by machine learning that are not being updated, developed, or refined in the process of use or deployment of methods and systems as described herein; and models that are being updated, developed, or refined by machine learning in the process of use or deployment of methods and systems as described herein.

[0085] A“deposit obtained as described herein will, in broad terms, be understood to be money associated with a loan, which loan may be referred to herein as a ‘primary loan’, wherein the money is not obtained via the primary loan. Suitably, the deposit, as described herein, facilitates a borrower of the primary loan obtaining the primary loan from a lender of the primary loan.

[0086] Typically, the deposit is sought by a borrower to obviate the need for lenders insurance for a primary loan, or at least substantially reduce the amount of lenders insurance payable for the primary loan. The deposit may additionally or alternatively be sought by a borrower to obviate the need for a‘family pledge’ or‘family guarantee’ or the like, as are known in the art, to obtain the primary loan.

[0087] In at least typical embodiments, the deposit obtained as described herein and an associated primary loan will be used by the borrower to purchase an asset. Typically, the asset is a real estate asset. Typically, the real estate asset is a residential property. In some typical embodiments, the residential property is, or is to be, a home for the borrower. In some embodiments, the residential property is, or is to be, an investment property or the like.

[0088] It will be understood that a deposit as described herein, particularly in the context of the purchase of real estate assets, may be alternatively referred to as a ‘downpayment’ or‘down payment’.

[0089] Typically, the primary loan is a relatively large loan, e.g. as assessed relative to income of the borrower. Typically, the primary loan is equivalent to at least 20% of the borrower’s total gross or net annual income. The primary loan may be equivalent to at least 30%, 40%, 50%, 60%, 70%, 80%, 90%, 100%, 150%, 200%, 300%, 400%, 500%, 600%, 700%, 800%, 900%, or 1000% of the borrower’s income. More typically, the primary loan is equivalent to between about 100% and about 500% of the borrower’s income. By way of non-limiting example, where the borrower’s total annual income is $100,000, in typical embodiments the primary loan may be between about $100,000 and about $500,000.

[0090] Typically, the deposit obtained as described herein is equivalent to less than 50% of the primary loan. The deposit may be equivalent to less than 5%, 10%, 15%, 20%, 25%, 30%, 35%, 40%, or 45% of the primary loan. More typically, the deposit is equivalent to between about 5% and about 25% of the primary loan. By way of non limiting example, where the primary loan is for $300,000, in typical embodiments the deposit may be between about $15,000 and about $75,000.

[0091 ] Typically, the deposit obtained as described herein is equivalent to less than 150% of the borrower’s total gross or net annual income. The deposit obtained may be equivalent to less than 5%, 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, 100%, 110%, 120%, 130%, or 140% of the borrower’s total annual income. More typically, the deposit is equivalent to between about 15% and about 75% of the borrower’s total gross or net annual income. By way of non-limiting example, where the borrower’s total gross or net annual income is $100,000, in typical embodiments the deposit may be between about $15,000 and $75,000.

[0092] Deposits obtained as described herein are obtained from a plurality of lenders. More particularly, it will be understood that obtaining a deposit as described herein involves obtaining respective “deposit loans” from each of a plurality of lenders. To avoid doubt, it will be understood that, at least in typical embodiments, each respective deposit loan will come from one of the plurality of lenders, and each respective deposit loan will provide a portion of the deposit obtained.

[0093] Typically, obtaining a deposit as described herein involves obtaining at least 2 deposit loans, more typically at least 3 deposit loans. In embodiments, obtaining the deposit includes or involves obtaining between about 5 and less than about 20 deposit loans, including about 6, 7, 8, 9, 10, 11 , 12, 13, 14, 15, 16, 17, 18, or 19 deposit loans. Alternatively, obtaining the deposit may involve obtaining between about 20 and less than about 100 deposit loans, including about 30, 40, 50, 60, 70, 80, and 90 deposit loans.

[0094] It will be appreciated that deposit loans obtained as described herein correspond to respective deposit loan offers from each of a plurality of lenders. It will be appreciated that more deposit loan offers than deposit loans may be obtained. In embodiments, obtaining the deposit includes or involves obtaining between about 5 and about 100 deposit loan offers, including about 6, 7, 8, 9, 10, 15, 20, 25, 30, 35, 40, 45, 50, 60, 70, 80, or 90 deposit loan offers. Alternatively, obtaining the deposit may include or involve obtaining between about 100 and about 1000 deposit loan offers, including about 200, 300, 400, 500, 600, 700, 800, and 900 deposit loan offers. Typically, each deposit loan offer is obtained from a unique lender, although without limitation thereto.

[0095] With the preceding in mind, Figure 1 sets forth steps of a method according to one aspect of the invention, method 1 .

[0096] Method 1 is a computational method of obtaining a deposit, including steps of creating a deposit loan profile 10; assessing the deposit loan profile 20; connecting the deposit loan profile with lenders 30; obtaining a deposit loan offer for the deposit loan profile 40; evaluating the deposit loan offer 50; and obtaining the deposit 60.

[0097] Borrower 2 and a plurality of lenders 3 interact with method 1 . For simplicity, interaction with one of the lenders 3 is depicted in Figure 1.

[0098] Borrower 2 may be a natural person, or a legal person such as a company. Typically, borrower 2 is one natural person, or two or more natural people seeking a deposit for a joint primary loan.

[0099] Typically, each lender 3 is a natural person. In some embodiments, lender 3 is a natural person known to borrower 2. In some embodiments, lender 3 is a natural person unknown to borrower 2. Alternatively, lenders 3 may include legal persons, such as company lending structures and/or self-managed super funds.

[0100] For the sake of clarity, although borrower 2 and lender 3 interact with method 1 , e.g. information is supplied by borrower 2 and lender 3 for the purposes of method 1 , actions take by borrower 2 and lender 3 need not form part of method 1. More generally, actions of borrowers or lenders need not form part of methods as described herein, unless the context requires otherwise and/or explicitly stated to the contrary.

[0101 ] Borrower 2 information is obtained to be used in the step of creating a deposit loan profile 10 as per method 1.

[0102] At least part of borrower 2 information may be obtained directly from borrower 2. Typically, information obtained directly from borrower 2 is provided by borrower 2 using an online or internet-based application form or the like, as will be known to those skilled in the art, such as using a graphical user interface (GUI).

[0103] At least part of borrower 2 information may be obtained indirectly from borrower 2. Typically, information obtained indirectly from borrower 2 is obtained using publicly available databases, such as websites or applications etc., e.g. social media websites or applications.

[0104] Borrower 2 information typically includes required deposit, i.e. the total value of the deposit that is required. Borrower 2 information may also include desired deposit loan conditions, e.g. interest rate payable, loan term, repayment frequency, etc.

[0105] Borrower 2 information typically further includes information on the primary loan for which the deposit is to be used, e.g. the size of the primary loan, interest rate payable on the primary loan, repayment frequency for the primary loan, asset(s) associated with the loan, etc.

[0106] Borrower 2 information also typically includes substantially standard borrower information required for financial borrowing, as will be known to those skilled in the art. By way of non-limiting example, borrower 2 information typically includes personal data such as name, address, nationality, residency status, relationship status, and number of dependents; income data, such as employment status, salary or wage, bonuses, and other sources of income; asset data, such as savings amount, and estimated value of vehicles, properties, and home contents; liability data, such as loans, credit card repayments, and family payments; and/or expenditure data, such as rent, electricity, water, and gas bills, telephone, tv, and internet bills, grocery bills, and entertainment expenses.

[0107] Borrower 2 information may further include social or demographic information. Non-limiting examples of social or demographic information include age, sex, gender, sexual preference, citizenship, primary language or communication method, first language spoken, country of birth, residency status, relationship status, marital status, number of dependent children, family composition, family type, household group, ethnicity, indigenous status, religious affiliation, education, recreational activities, health issues, criminal record, social or demographic characteristics of parents, social or demographic characteristics of siblings, social or demographic characteristics of extended family, and social or demographic characteristics of friends.

[0108] Borrower 2 information may also include information regarding preferred or desirable lenders 3. In some embodiments, borrower 2 may identify any preference for persons known to borrower 2 as lenders 3, e.g. family, friends, or acquaintances.

[0109] In some typical embodiments, borrower 2 information may include preferred or desired characteristics of lenders 3, e.g. financial status, social or demographic characteristics, lending history, geographical location, etc. In some typical embodiments, borrow 2 information on preferred or desired characteristics of lenders 3 is produced using a machine learning model. Typically, other borrower 2 information such as hereinabove described is processed using a machine learning model to produce information on preferred or desired characteristics of lenders 3. [01 10] In some typical embodiments, social or demographic information for borrower 2 is processed using a machine learning model to produce information on preferred or desired characteristics of lenders 3. Typically, the preferred or desired characteristics of lenders 3 are or include social or demographic characteristics of lenders 3.

[01 1 1 ] The step of creating a deposit loan profile 10 as per method 1 includes indexing borrower 2 information such as hereinabove described to the deposit loan profile.

[01 12] Indexing for step 10 is performed computationally using a database structure, as are known in the art. Typically, indexing for step 10 and/or other steps as hereinbelow described involves permanent data storage using scalable object relational model (ORM) database technology.

[01 13] A range of suitable databasing software, and modifications thereof, may be appropriate for the purposes of step 10 and/or other indexing steps as hereinbelow described. By way of non-limiting example, open source software that may be appropriate for indexing include MySQL, Microsoft SQL, PostgreSQL, Teradata Database, SAP HANA, Express Edition, MongoDB, CouchDB, DynamoDB, MarkLogic, RethinkDB, ArangoDB, Neo4j, OrientDB, Titan, Cayley, Hive, and Elasticsearch may be suitable. By way of non-limiting example, proprietary software that may be appropriate for indexing include ADABAS, Alpha Five, Borland Database Engine, Clusterpoint, Cornerstone, Datablitz, DataPerfect, DBase, EXtremeDB, FileMaker, FoxPro, Gemstone, Helix, InfinityDB, Kinetica, Mimer SQL, NexusDB, NitrosBase, ObjectDatabase++, Oracle Database, Paradox, Polyhedra DBMS, PrimeBase, R:Base, Rocket U2, SharePoint, SQL Anywhere, Starcounter, TeraText, TurbolMAGE, Vectorwise, and XDB Enterprise. In some typical embodiments, PostgreSQL or Oracle Database software is used for the purposes of step 10 and/or other indexing steps.

[01 14] The step of assessing the deposit loan profile 20 as per method 1 typically includes steps of calculating a risk rating for the deposit loan profile 21 ; and approving (accepting) or denying (rejecting) the deposit loan profile 22.

[01 15] Suitably, calculating a risk rating as per step 21 uses information indexed to the deposit loan profile as per step 10. Typically, the risk rating is calculated following an approach which may be referred to as the‘five Cs of credit’, or similar, (character, capacity, capital, conditions and collateral), as is known in the art. Typically, risk scores or the like, e.g. a 1 -10 score with 10 being the highest risk, are determined for respective criteria, such as said respective Ό’ criteria.

[01 16] An overall categorical risk rating may be calculated as per step 21 , such as selected from very low risk (or‘A’ category or the like); low risk, (or‘B’ category or the like); moderate risk (or‘C’ category or the like); high risk (or Ό’ category or the like); and very high risk (or Έ’ category or the like). Additionally or alternatively, an overall numerical risk rating may be calculated as per step 21 , such as a percentile risk rating.

[01 17] As hereinabove described, the step of calculating a risk rating for the deposit loan profile 21 typically includes assessing the borrowing capacity of borrower 2. The borrowing capacity of borrower 2 is assessed using data indexed to the deposit loan profile, as hereinabove described.

[01 18] In general terms, the skilled person will appreciate that assessing borrowing capacity of a borrower, such as borrower 2, incorporates a calculation similar to the following.

X = A - B - C - D - E- F where:

X= budget surplus;

A = gross income;

B = tax;

C = existing liabilities;

D = new liabilities (if loan is granted)

E = living expenses;

F= a buffer value

[01 19] It will be appreciated by the skilled person that, for the purpose of calculations such as the above in the context of method 1 , the primary loan will typically be considered an existing liability.

[0120] The step of approving or denying the deposit loan profile 22 is based, at least in part, on the risk rating calculated as per step 21. [0121 ] Approval as per step 22 according to method 1 is typically subject to conditions, which conditions are determined, at least in part, by the risk rating calculated as per step 21. The conditions typically include a condition selected from deposit loan amount, deposit loan term, deposit loan repayment frequency, and deposit loan interest rate. Approval as per step 22 typically requires one or more conditions to fall within a specified range. Upper and lower boundaries may be specified for the conditions.

[0122] The skilled person will appreciate that a range of software, and modifications thereof, may be appropriate for use as per steps 20-22 of method 1. Non-limiting examples of software that may be appropriate include TurnKey Lender, Decisions, ADP, Calyx Point, Loandisk, FINFLUX, HES Lending Platform, FUNDINGO, Lending360, SAIL Indirect, VCO Lend, Provenir Platform, Cortex, Solar, AMB, LendFoundry, Allegro Lending Suite, Whitelabel Funding, Flelium, Lending Script, and Thrinacia.

[0123] In some typical embodiments, a machine learning model is used as per steps 20-22, either alone or in conjunction with other suitable software and/or modifications thereof, such as listed above.

[0124] In some embodiments, a machine learning model is used to calculate, adjust, or modify the risk rating calculated as per step 21 and/or approval status as per step 22, subject to the suitability of available lenders 3 given borrower 2 information on desired characteristics of lenders 3.

[0125] Information associated with the step of assessing the deposit loan profile 20, including the risk rating calculated as per step 21 , approval status as per step 22, and conditions to which the approval is subject, is typically indexed to the loan deposit profile as per method 1. To avoid doubt, for the purposes of method 1 , said indexing may be considered part of step 10, or as a separate step 23 as depicted in Figure 1.

[0126] According to method 1 , if the deposit loan profile is approved as per step 22, the step of connecting the deposit loan profile with lenders 30 is performed.

[0127] In some typical embodiments of method 1 , prior to the step of connecting the deposit loan profile with lenders 30, steps of creating potential lender profiles 15; and/or matching potential lenders with the deposit loan profile 25 are performed. Details of these optional steps are provided in Figure 2. [0128] With reference to Figure 2, in embodiments of method 1 including optional steps 15 and/or 25, in addition to borrower 2 and lenders 3, a plurality of potential lenders 4 interact with method 1. For simplicity, interaction with one of the potential lenders 4 is depicted in Figure 2.

[0129] Typically, each potential lender 4 is a natural person. In some embodiments, potential lender 4 is a natural person known to borrower 2. In some embodiments, potential lender 4 is a natural person unknown to borrower 2. Alternatively, potential lenders 4 may include legal persons, such as company lending structures and/or self- managed super funds.

[0130] With reference to the description provided hereinabove, it is typical for between about 5 and about 100 lenders 3 to provide deposit loan offers in the context of method 1. It will be understood that embodiments of method 1 including optional steps 15 and/or 25 typically involve between about 2x and about 1000x, including about 5x, 10x, 15x, 25x, 50x, 75x, 100x, 150x, 200x, 350x, 500x, 650x, and 800x, the number of potential lenders 4 as compared to the number of lenders 3.

[0131 ] By way of non-limiting example, an embodiment of method 1 involving 50 lenders 3 may involve between about 100 (2x) and about 50,000 (1000x) potential lenders 4.

[0132] Typically, each potential lender 4 is associated with a respective potential lender profile. It will be understood that the potential lender profiles may be created according to embodiments of method 1 , as hereinbelow described. Alternatively, pre existing potential lender profiles may be accessed, which will suitably contain similar information as hereinbelow described.

[0133] Focusing on optional step 15, in embodiments of method 1 including step 15 of creating lender profiles, lender profiles are created for a plurality of potential lenders 4, similar as hereinabove described in relation to creation of a deposit loan profile for borrower 2.

[0134] It will be appreciated that at least part of potential lender 4 information for each of the respective potential lenders 4 may be obtained directly from potential lenders 4. Typically, information obtained directly from potential lender 4 is provided by potential lender 4 using an online or internet-based application form or the like, as will be known to those skilled in the art, such as using a graphical user interface (GUI). [0135] It will be further appreciated that at least part of potential lender 4 information may be obtained indirectly from potential lender 4. Typically, information obtained indirectly from potential lender 4 is obtained using publicly available databases, such as websites or applications etc., e.g. social media websites or applications.

[0136] Potential lender 4 information may include preferred required deposit, i.e. preferences with respect to the total value of the deposit that is required by a borrower e.g. borrower 2. Potential lender 4 information may also include preferred conditions for a deposit loan required by a borrower e.g. borrower 2, e.g. interest rate payable; loan term; repayment frequency, etc.

[0137] Potential lender 4 information may further include preferences for the primary loan for which the deposit is to be used, e.g. the size of the primary loan, interest rate payable on the primary loan, repayment frequency for the primary loan; asset(s) associated with the loan, etc.

[0138] Potential lender 4 information may include information typically required in the context of financial borrowing and lending, as will be known to those skilled in the art. By way of non-limiting example, potential lender 4 information may include personal data such as name, address, nationality, resident status, relationship status, and number of dependents; income data, such as employment status, salary or wage, bonuses, and other sources of income; asset data, such as savings amount, and estimated value of vehicles, properties, and home contents; liability data, such as loans, credit card repayments, and family payments; and/or expenditure data, such as rent, electricity, water, and gas bills, telephone, tv, and internet bills, grocery bills, and entertainment expenses.

[0139] Potential lender 4 information may include social or demographic information. Non-limiting examples of social or demographic information include age, sex, gender, sexual preference, citizenship, primary language or communication method, first language spoken, country of birth, residency, relationship status, marital status, number of dependent children, family composition, family type, household group, ethnicity, indigenous status, religious affiliation, education, recreational activities, health issues, criminal record, social or demographic characteristics of parents, social or demographic characteristics of siblings, social or demographic characteristics of extended family, and social or demographic characteristics of friends. [0140] Potential lender 4 information may include information regarding preferred borrowers e.g. borrower 2. In some embodiments, potential lender 4 may indicate any preference for lending to persons known to potential lender 4, such as family, friends, or acquaintances. In some embodiments, potential lender 4 may identify preferred characteristics for borrowers, e.g. financial status, social or demographic characteristics, borrowing history, geographical location, etc.

[0141 ] In some typical embodiments, information on preferred or desirable characteristics of borrowers is produced using a machine learning model. Typically, other potential lender 4 information such as hereinabove described is processed using a machine learning model to produce information on preferred or desirable characteristics of borrowers.

[0142] In some typical embodiments, social or demographic information for potential lenders 4 is processed using a machine learning model to produce information on preferred or desirable characteristics of borrowers. Typically, the preferred characteristics of the borrowers are or include social or demographic characteristics of the borrowers.

[0143] It will be further appreciated that the optional step of creating potential lender profiles 15 as per method 1 includes indexing potential lender 4 information such as hereinabove described to a corresponding potential lender profile, substantially as hereinabove described in the context of the step of creating a deposit loan profile 10.

[0144] Focusing now on optional step 25, in embodiments of method 1 including matching potential lenders with the deposit loan profile 25, typically, potential lender profiles for potential lenders 4 are compared with the deposit loan profile of borrower 2. To avoid doubt, for the purposes of method 1 , said comparing may be considered part of step 25, or as a separate step 251 as depicted in Figure 2.

[0145] It will be appreciated that optional step 25 is typically performed for the purpose of identifying a subset of potential lenders 4 to select as suitable lenders and become lenders 3. To avoid doubt, for the purposes of method 1 , said selection of suitable lenders may be considered part of step 25, or as a separated step 252 as depicted in Figure 2.

[0146] In general terms, to select suitable potential lenders 4 to become lenders 3, the quality of matching, or degree of complementarity, of a potential lender profile of a given potential lender 4 with the deposit loan profile of borrower 2 is assessed. [0147] In embodiments, similarities or differences between desired or preferred primary and/or deposit loan characteristics are used to determine complementarity of a potential lender profile with the deposit loan profile.

[0148] In embodiments, complementarity between preferred lender information of the deposit loan profile and preferred borrower information of a potential lender profile is used to determine complementarity of a potential lender profile and the deposit loan profile.

[0149] In embodiments, complementarity between information of the deposit loan profile and information of a potential lender profile is determined using a machine learning model. Typically, the machine learning model is used to determine complementarity between information including social or demographic characteristics.

[0150] Typically, selection of suitable lenders 252 includes ranking or prioritising potential lenders 4 based on the degree of complementarity of the potential lender profiles and the deposit loan profile. It will be appreciated that, typically, a subset of relatively highly ranked or highly prioritised potential lenders 4 are selected as per step 252 to become lenders 3.

[0151 ] In some embodiments of method 1 the outcome of assessment of the deposit loan profile 22 may be changed, altered, or modified subject to the outcome of selection of suitable lenders 252. To avoid doubt, for the purposes of method 1 , altering the outcome of assessment of the deposit loan profile may be considered part of step 25, part of step 20, or a separate step 253 as depicted in Figure 2.

[0152] By way of non-limiting example, if characteristics of potential lenders 4 are considered particularly unfavourable, e.g. due to a low number of suitable potential lenders 4 and/or low complementarity between respective potential lender 4 profiles and the deposit loan profile, the outcome may be changed from accepted to rejected. Alternatively, if characteristics of potential lenders 4 are considered particularly favourable, e.g. due to a high number of suitable potential lenders 4 and/or high complementarity between respective potential lender 4 profiles and the deposit loan profile, the outcome may be changed from rejected to accepted.

[0153] Looking again now at Figure 1 , as per step 30 of method 1 , the deposit loan profile is connected with the plurality of lenders 3. Typically, step 30 includes providing one or more security-protected data links, e.g. URL links, to the plurality of lenders 3. The link provided according to step 30 enables access by lender 3 to at least some of the information indexed to the deposit loan profile as per step 10 and/or step 23, typically including conditions subject to which the deposit loan profile is approved. It will be appreciated that when lender 3 accesses a link provided as per step 30 of method 1 , lender 3 can review the applicable information indexed to the deposit loan profile and consider submitting a deposit loan offer.

[0154] The step of obtaining a deposit loan offer for the deposit loan profile 40 according to method 1 includes receiving a deposit loan offer from lender 3. The deposit loan offer is typically received via the security-protected data link provided to lender 3 according to step 30.

[0155] In some typical embodiments, a deposit loan offer obtained from lender 3 according to step 40 is obtained in conjunction with, or otherwise associated with, information on the lender 3, such as lender or potential lender information hereinabove discussed.

[0156] The deposit loan offer obtained according to step 40 is typically indexed to the deposit loan profile as per method 1. To avoid doubt, for the purposes of method 1 said indexing may be considered part of step 10, or as a separate step 41 as depicted in Figure 1 . In embodiments wherein the deposit loan offer according to step 40 is associated with information on the lender 3, suitably, the information on lender 3 is indexed to the deposit loan profile.

[0157] The step of evaluating the deposit loan offer 50 according to method 1 is performed when a deposit loan offer from lender 3 is obtained according to the step 40. Step 50 typically includes steps of communicating the deposit loan offer to the borrower 51 ; communicating acceptance or rejection of the deposit loan offer to the deposit loan profile 52; and communicating acceptance or rejection of the deposit loan offer to the lender 53.

[0158] In some typical embodiments of method 1 , prior to indexing of the deposit loan offer to the deposit loan profile 41 and/or communicating the deposit loan offer to the borrower 51 , steps of creating lender profiles 16; and/or prioritising deposit loan offers 45 are performed. Details of these optional steps are provided in Figure 3.

[0159] In embodiments of method 1 described with reference to Figure 3, it will be understood that each potential lender 3 is typically associated with a respective lender profile. It will be understood that the lender profiles may be created according to embodiments of method 1 including step 16, as hereinbelow described. Alternatively, pre-existing lender profiles may be accessed, which will suitably contain similar information as herein described.

[0160] The step of creating lender profiles 16 is substantially as hereinabove described for the step of creating of potential lender profiles 15, with reference to Figure 2. It will be appreciated that, in embodiments including step 15, potential lender profiles created for potential lenders 4 can also serve as lender profiles in the context of step 16. That is, with reference to Figure 2, a profile for a particular potential lender 4 in accordance with step 15 can be used as a profile for a lender 3 in accordance with step 16, in the instance that the potential lender 4 is selected as a lender 3.

[0161 ] The step of prioritising deposit loan offers 45 typically includes optimising the suitability of deposit loan offers for borrower 2. Additionally or alternatively, the step of prioritising deposit loan offers may include prioritising deposit loan offers for one or more lenders 3.

[0162] In some typical embodiments, the step of prioritising deposit loan offers according to step 45 is based, at least in part, on a condition subject to which the loan offer is obtained. Typical said embodiments involve receiving competitive loan offers from the plurality of lenders 3.

[0163] In some typical embodiments, the step of prioritising deposit loan offers includes prioritising deposit loan offers subject to relatively lower interest rates ahead of deposit loan offers subject to relatively high interest rates. For example, a deposit loan offer subject to a minimum interest rate of 6% per annum, may be prioritised over a deposit loan offer subject to a minimum interest rate of 7% per annum.

[0164] In some typical embodiments, the step of prioritising deposit loan offers includes prioritising deposit loan offers subject to quality of matching or degree of complementarity of a lender profile of a given lender 3 with the deposit loan profile of borrower 2, similar as hereinabove described with reference to step 25 and Figure 2.

[0165] In embodiments, similarities or differences between preferred or desired primary and/or deposit loan characteristics are used to determine complementarity of a lender profile with the deposit loan profile.

[0166] In embodiments, complementarity between preferred lender information of the deposit loan profile and preferred borrower information of a lender profile is used to determine complementarity of a lender profile for lender 3 and the deposit loan profile.

[0167] In embodiments, complementarity between the deposit loan profile and a lender profile for a given lender 3 is determined using a machine learning model. Typically, the machine learning model is used to determine complementarity between information including social or demographic characteristics, although without limitation thereto.

[0168] It will be understood that, typically, a subset of prioritised deposit loan offers is selected for the step of indexing of the deposit loan offer to the deposit loan profile 41 and/or communicating the deposit loan offer to the borrower 51.

[0169] Looking again now at Figure 1 , it will be appreciated that when the step of communicating the deposit loan offer to the borrower 51 is performed, the borrower 2 can review the deposit loan offer and accept or reject the offer. When borrower 2 accepts or rejects the deposit loan offer, the steps of communicating acceptance or rejection of the deposit loan offer the deposit loan profile 52 and the lender 53 are performed.

[0170] Acceptance or rejection of the deposit loan offer by the borrower is typically indexed to the loan deposit profile as per method 1. To avoid doubt, for the purposes of method 1 , said indexing may be considered part of step 10, or a separate step 54 as depicted in Figure 1.

[0171 ] According to method 1 , typically, when communication of acceptance of deposit loan offers to the deposit loan profile as per step 52 occurs that amount, in total, to the full required amount of the deposit, the step of obtaining the deposit 60 is performed. Step 60 of method 1 typically includes steps of arranging contracts for the deposit loan profile 61 ; receiving deposit loan funds from a lender to the deposit loan profile 62; and transferring deposit loan funds from the deposit loan profile to the borrower 63.

[0172] Step 61 typically includes communicating a lender contract for execution to, and obtaining an executed contract from, lender 3. Step 61 typically includes communicating a borrower contract for execution to, and obtaining an executed contract from, borrower 2. The borrower and lender contract(s) are typically digital or electronic contracts. [0173] Information associated with the step of obtaining the deposit 60, including contracts obtained as per step 61 , deposit loan funds received as per step 62, and deposit loan funds transferred as per step 63, is typically indexed to the loan deposit profile as per method 1. To avoid doubt, for the purposes of method 1 , said indexing may be considered part of step 10 or a separate step 64 as depicted in Figure 1.

[0174] Typically, at least steps 20-60, or at least steps 30-60, of method 1 will be performed using a software package, as further discussed hereinbelow. In embodiments, the software package comprises or otherwise incorporates machine learning model(s) for optimised matching between borrower 2 and lenders 3.

[0175] As depicted in Figure 1 , method 1 may optionally include a further step of obtaining a repayment for the deposit loan profile 70. Typically, step 70 includes steps of receiving repayment funds from the borrower to the deposit loan profile 71 ; and transferring the repayments funds to the lender 72.

[0176] Repayments obtained are typically indexed to the deposit loan profile as per method 1. To avoid doubt, for the purposes of method 1 said indexing may be considered part of step 10, or a separate step 73 as depicted in Figure 1.

[0177] For illustrative purposes, Figure 4A provides a flow chart incorporating an implementation of method 1.

[0178] It will be appreciated that the flow chart in Figure 4A is presented as a continuous process, which is described as follows with reference to the steps of method 1 as set out in Figure 1.

[0179] It will be further appreciated that, in some typical embodiments of the implementation of method 1 shown in Figure 4A, machine learning models are used as described in detail above with reference to Figure 1.

[0180] As depicted in Figure 4A, a borrower provides information to be used in step 10 of creating a deposit loan profile, in the form of completing an application. As per step 10, information provided in the application is indexed to the deposit loan profile. In this implementation, the information is also used for an application for an associated primary loan.

[0181 ] The indexed information is used in the step of assessing the deposit loan profile 20, which includes performing a credit check, servicing check, spending history check (as part of an asset and liability review), employment check, and security review. A risk rating is calculated as per step 21 ; and a decision is made on the deposit loan profile as per step 22. If the deposit loan profile is denied (rejected), no further steps of method 1 occur. If the deposit loan profile is approved (accepted), the step of connecting the deposit loan profile to a plurality of potential lenders 30 is performed.

[0182] Step 30 includes providing a security-protected URL link to a plurality of lenders or potential lenders. As depicted in Figure 4A, the borrower communicates whether the deposit loan profile is to be connected to lenders or potential lenders privately (private loan offer) or publicly (open loan offer). Where the deposit loan profile is connected privately, links are distributed by way of private invitation to individual lenders or potential lenders known to the borrower ( e.g . acquaintances, friends, or family members). Private invitations may be supplemented with optional invitations to wholesale investors, typically known to a service provider of method 1.

[0183] Lenders or potential lenders to whom the links are distributed can review the applicable information indexed to the deposit loan profile (review loan proposal) and consider submitting a deposit loan offer.

[0184] Where lenders or potential lenders decide to submit a deposit loan offer (loan proposal accepted) respective deposit loan offers are obtained for the deposit loan profile as per step 40. The respective deposit loan offers may be subject to the same (fixed rate) or a different (dynamic bidding) interest rate.

[0185] When a deposit loan offer is obtained according to step 40, the step of evaluating the deposit loan offer 50 is performed. Step 50 includes the step of communicating the deposit loan offer to the borrower 51 (loan offer made). To avoid doubt, each individual deposit loan offer may be communicated to the borrower, or a composite deposit loan offer totalling the desired deposit amount may be communicated to the borrower.

[0186] In some typical embodiments, deposit loan offers are prioritised for communication to the borrower based, at least in part, on an interest rate subject to which the deposit loan offers are made. Prioritisation based on interest rate may be facilitated by a dynamic bidding process, which processes are known generally in the art. By way of elaboration, deposit loan offers may be made subject to a minimum required interest rate by the lender. On this basis, a selected number of deposit loan offers are chosen, wherein the interest rate associated the respective deposit loan offer is determined based on the relative minimum required interest rates of each of the lenders. It will be appreciated that, in said embodiments, the deposit loan offers will be competitive deposit loan offers.

[0187] When a deposit loan offer or composite deposit loan offer is communicated to a borrower as per step 51 , the borrower can review and accept or reject the offer. Acceptance or rejection of the deposit loan offer is communicated to the deposit loan profile as per step 52, and the potential lender as per step 53.

[0188] When respective deposit loan offers, or a composite deposit loan offer, sufficient to provide the required amount of the deposit are accepted, the step of obtaining the deposit 60 is performed. Step 60 includes steps of obtaining contracts for the deposit loan profile 61 (new loan documented); receiving deposit loan funds from each lender to the deposit loan profile 62; and transferring deposit loan funds from the deposit loan profile to the borrower 63 (loan settlement).

[0189] Figure 4B provides a further flow chart incorporating an implementation of method 1. The implementation of method 1 illustrated in Figure 2B is similar to that of Figure 2A. Flowever, in Figure 2B, the results of the credit check, servicing check, asset and liability review, employment check, and security review are provided to both the deposit loan profile and a primary lender.

[0190] Typically, the method of this aspect is for obtaining a real estate deposit, such as a home loan deposit, although without limitation thereto. Figure 5 shows a simplified schematic incorporating an embodiment of method 1 , wherein a home is purchased.

[0191 ] As depicted in Figure 5, in this embodiment, method 1 is for obtaining a deposit in the form of deposit 5, associated with a primary loan in the form of home loan 50. Together, the deposit 5 and the home loan 50 are used to purchase home 500. Flome loan 50 is sourced from traditional lender 100, such as a bank. Deposit 5 is obtained using method 1 to obviate the need for Lenders Mortgage Insurance (LMI) to obtain home loan 50. It is typical for method 1 to be implemented in conjunction with an application for home loan 50, when an offer for purchase of home 500 has been accepted subject to finance.

[0192] The relative amounts of home loan 50 and deposit 5 will be determined, at least in part, by the size of deposit traditional lender 100 requires to obviate the need for LMI. Generally, although without limitation, deposit 5 will be the smallest deposit required to obviate the need for LMI. By way of example, where traditional lender 100 requires 20% deposit to obviate the need for LMI, and the purchase price of home 500 is $500,000, deposit 5 may be $100,000 and home loan 50 may be $400,000. It will be appreciated that, in this scenario, deposit 5 is equivalent to 20% of the purchase price of home 500, and equivalent to 25% of home loan 50.

[0193] The skilled person will readily appreciate that the specific circumstances of implementation of method 1 in the context of purchasing real estate can vary, and may be substantially more complex than depicted in Figure 5. Accordingly, additional examples are provided as follows, for illustrative purposes.

[0194] Figure 6 depicts a schematic showing another implementation of an embodiment of method 1 in the context of purchasing real estate. As shown in this schematic, the borrower interacts with a seller (e.g. a real estate agent or developer etc.) and/or a broker or advisor. Funds for the purchase of real estate may include, in addition to the primary loan and the deposit obtained using method 1 , savings and/or a first home owner’s grant or the like, and/or a further loan from another secondary lender.

[0195] Using a schematic based on that depicted in Figure 6, Figure 7 provides a further example of implementation of an embodiment of method 1 in the context of purchasing real estate, wherein the deposit is obtained as part of refinancing a property. The embodiment of method 1 depicted in Figure 7 includes further steps 150 of valuing the property to be refinanced; and 160 of assessing the borrower’s equity in the property to be financed.

[0196] Steps 150 and 160 as per the embodiment of method 1 depicted in Figure 7 may be performed using a range of suitable software resources. Typically, steps 150 and 160 are performed by accessing one or more suitable online resources, as will be known to those skilled in the art. Accordingly, in the embodiment of method 1 depicted in Figure 7, step 150 is in the form of an online automated system home valuation; and step 160 is in the form of an online automated system home equity calculator. By way of non-limiting example, for the Australian housing market, online resources for property valuation and equity calculation are made available by propertyvalue.com.au; realestate.com.au; domain.com.au; openagent.com.au; choice.com.au; and homeguru.com.au. [0197] In some typical embodiments, a machine learning model is used, typically in conjunction with suitable software resources such as set out above, for the purpose of steps 150 and 160.

[0198] In the embodiment of method 1 depicted in Figure 7, value of and equity in the property assessed as per steps 150 and 160 are indexed to the deposit loan profile. In Figure 7, value of and equity in the property are communicated by a broker or advisor, however this information may alternatively be communicated directly. Said indexing may be considered part of step 10 of method 1 , or as a separate indexing step.

[0199] It will be further understood that, in the embodiment of method 1 depicted in Figure 7, value of and/or equity in the property to be refinanced assessed as per steps 150 and/or 160 is used for assessing the deposit loan profile according to step 20.

[0200] Using a schematic based upon that depicted in Figure 6, Figure 8 provides a further example of implementation of an embodiment of method 1 in the context of purchasing a real estate, including a further step 650 of transferring the deposit to a new property.

[0201 ] Step 650 according to this embodiment of method 1 is typically performed in conjunction with sale of the original property and/or purchase of the new property (typically subject to finance) by the borrower. Transfer of the deposit according to step 650 is indexed to the deposit loan profile. Said indexing may be considered part of step 10 or as a separate step.

[0202] Looking now at Figure 9, this figure depicts an embodiment of a system of the invention, system 1000. System 1000 is adapted to perform method 1 as hereinabove described, interacting with borrower 2, lenders 3, and (optionally) potential lenders 4 (not shown). System 1000 includes processor 1 100; receiver 1200; transmitter 1300; input component 1400; and storage component 1500. Receiver 1200, transmitter 1300, input component 1400, and storage component 1500 are connected to processor 1 100, e.g. by wired or wireless connection.

[0203] Processor 1 100 is adapted to run suitable software for the purposes of method 1 , as exemplified and discussed herein. Receiver 1200 and transmitter 1300 facilitate internet connection of system 1000, and are typically of a modem or the like. Input component 1400 typically comprises a keyboard and/or mouse or the like. Storage component 1500 is adapted to securely store and maintain a deposit loan profile and may be, for example, a solid state or disc drive.

[0204] Typically, in use, system 1000 receives information from borrower 2 in the form of an online deposit loan application via internet connection 1200. The information from the online deposit loan application is used by processor 1 100 to create a deposit loan profile, with the information arranged in a database structure using suitable software such as herein described. Manual data entry and/or editing by an operator using input component 1400 may be used to assist creation of the deposit loan profile. The deposit loan profile is stored using storage component 1500.

[0205] Processor 1 100 assesses the deposit loan profile using information databased as per the deposit loan profile. Suitable software as herein described is used by processor 1100 to create a risk rating for the deposit loan. Calculation of the risk rating may involve, or be complemented with, third party checking, such as credit checking, servicing checking, employment checking, and the like. Third party checking may be facilitated by exchange of data to and from system 1000 to an applicable third party using modem 1200/1300. Manual data entry and/or editing by an operator using input component 1400 may be used to assist assessment of the deposit loan profile.

[0206] Assessment of the deposit loan profile using processor 1 100 results in approval or denial of the deposit loan profile.

[0207] Where the deposit loan profile is approved, a secured data link, e.g. URL link, is transmitted to each lender 3 using modem 1200/1300, wherein each lender 3 can review information associated with the deposit loan profile. In some typical embodiments, the deposit loan profile is compared with a plurality of lender profiles of potential lenders 4 (not shown) from which lenders 3 are selected, prior to transmission of the data link to each lender 3. Suitably processor 1 100 applies a machine learning model to compare lender profiles of potential lenders 4 (not shown) with the deposit loan profile, for the purpose of selecting lenders 3.

[0208] Each lender 3 can submit a deposit loan offer to the deposit loan profile using the secured link. Deposit loan offers are communicated with and accepted or rejected by borrower 2 via modem 1200/1300. Deposit loan offers may be communicated individually to borrower 2, or communicated as a composite deposit loan offer when a plurality of deposit loan offers totalling the required deposit amount are obtained. [0209] In some typical embodiments, deposit loan offers from lenders 3 are prioritised, prior to communicating the deposit loan offers to borrower 2. Suitably, processor 1 100 applies a machine learning model to compare deposit loan offers and/or lender profiles of lenders 3, for the purpose of prioritising deposit loan offers from lenders 3.

[0210] When deposit loan offers totalling the required deposit amount are accepted, processor 1 100 communicates loan contracts between the deposit loan profile, borrower 2, and lenders 3; and deposit funds are transferred from lenders 3 to borrower 2 via the deposit loan profile. Manual data entry and/or editing by an operator using input component 1400 may be used to assist with the communicating of contracts and transferral of funds.

[021 1 ] The deposit loan profile stored using storage component 1500 is updated with applicable details during use, such as details of assessment of the deposit loan profile; deposit loan offers submitted by lenders 3; acceptance or rejection of deposit loan offers by borrower 2; loan contracts communicated; and funds transferred.

[0212] Certain advantages of methods and systems as described herein will now be described, without limitation. In general terms, the use of method 1 for obtaining a deposit can have advantages for a borrower, such as borrower 2, as follows:

[0213] No lenders insurance: obtaining the deposit can eliminate the need for lenders insurance.

[0214] Privacy: the deposit loan profile can be shared privately with potential lenders chosen by the borrower.

[0215] Portability: the deposit obtained can be transferred between assets.

[0216] Interest rates: e.g. home loans for less than 80% loan to value ratio (LVR) often have substantially lower interest rates than those for greater than 80% LVR.

[0217] Refinance options: absence of the need for lenders insurance often allows for interest rate advantages when refinancing a primary loan.

[0218] Negotiation: absence of the need for lenders insurance often allows better loan terms to be negotiated with a lender of a primary loan.

[0219] Choices of primary lender: absence of the need for lenders insurance often allows greater choice of lenders for a primary loan.

[0220] Avoid family guarantee: the deposit can be obtained without potential risk associated with traditional use of a family member acting as guarantor. [0221 ] Faster home ownership: the deposit obtained can allow for a home to be purchased more quickly than using traditional approaches.

[0222] Equity building: absence of lenders insurance can allow for greater flexibility for equity building by the strategic selling and buying of assets, e.g. real estate.

[0223] Avoid profit sharing: the deposit can be obtained without the need for profit- sharing or co-ownership agreements.

[0224] As hereinabove described, typically, at least steps 20-60 or 30-60 of method 1 of the invention can be performed using a software package. Advantageously, the software package can incorporate machine learning models.

[0225] Advantageously, the software package can be adapted to assess information provided by both borrowers and lenders to provide the best possible outcomes for the borrower and lender, for example in terms of risk profile, loan serviceability, proportions of the loan total to be supplied by individual lenders, assessing data against previous historical outcomes, and incorporating data available on all parties involved from multiple third party sources.

[0226] Advantageously, the software package can be adapted to match specific borrower requirements against lender characteristics. In some typical embodiments, algorithms will retrieve data from internet accessible data sources {e.g. social media platforms and the like, such as Facebook, Linkedln, Twitter) to provide additional data for decision making processes, to assist evaluation of the suitability of borrower and lender matching, on both sides of the transaction.

[0227] In the context of methods and systems as described herein, the software package can advantageously reduce the need for manual intervention currently required for traditional loan processing. In typical embodiments, the software package will incorporate artificial intelligence or self-learning functionality, which may result in substantial gains in efficiency and efficacy for borrowers and/or lenders. The self-learning functionality may be audited manually.

[0228] Advantageously, the software package may be backed by an Application Programming Interface (API) or the like, that controls authentication of licenced third parties and/or provides system extensibility allowing third party developers to augment functionality.

[0229] Advantageously, method 1 and system 1000 are adapted to allow borrowers and lenders to provide information for use according to the invention computationally, typically via a graphical user interface (GUI). In some typical embodiments, GUI interface(s) for the borrower and/or lender may be incorporated into the software package as hereinabove described. Advantageously, the GUIs may provide direct messaging capabilities between the lender and the borrower, while keeping identity anonymous and information anonymised.

[0230] It will be appreciated that, while some embodiments of method 1 as described herein incorporate manual processing, such as in the context of data handling and/or review, method 1 is advantageously adapted for fully automated implementation. The skilled person will appreciate that method 1 is advantageously well-suited to interact with developments in e-conveyancing and the like ( e.g . PEXA). Method 1 and system 1000 are readily suited for use in the context of fully automated asset transactions, such as in the context of real estate.

[0231 ] As hereinabove described, a range of machine learning approaches can be used in the context of methods and systems described herein. Further detail in the context of developing and applying suitable machine learning models in these contexts is provided as follows

[0232] Typically, machine learning models are prepared for a training phase with an assortment of relevant data such as from borrowers and/or lenders. The data gathering process can advantageously incorporate methods of analysing a range of signals from a variety of sources including available social signals, bank statements, credit history, property values, economic signals (national and global), spending habits, anonymised available lenders, anonymised borrower applications, primary and secondary borrower and lender responses and known prior outcomes of existing loans.

[0233] Typically, the training input data, potentially together with live data post training is flattened, labelled and categorically homogenised using configurable parameters that allow disparate sources to be labelled and adjusted as further data sets become available to ingest.

[0234] Typically, input data once prepared us run through a variety of algorithms that will typically be suitable for processing both text and numerical data. Further algorithms can be incorporated as further suitable input sources become available. [0235] Typically, in order to reduce training time and/or data size, training is run through a series of convolutions allowing large datasets to be processed faster and more accurately.

[0236] Typically, initial prediction results are evaluated for accuracy over an algorithmically chosen selection of the data. Manually evaluated prediction results can be divided into malleable categories that provide the ability to analyse predictions, such as based on probability of a loan being granted. Typically, after the completion of each training run hyperparameters are tuned to ensure that accuracy of the models continues to increase over time.

[0237] Typically, after initial training of the machine learning completes, the system will be provided access to all required live data sources.

[0238] Typically, machine learning model results will be be manually analysed and incorrect predictions will be adjusted. Machine learning algorithms will typically be able to ingest adjusted predictions in order to increase accuracy.

[0239] Typically, consistent further training takes place with live data as previously deployed borrowing and lending arrangements are monitored, providing feedback on the accuracy of the machine learning model predictions in the real world. Using this real-world feedback loop, machine learning models can be updated and improved to obtain improved higher accuracy of subsequent predictions.

[0240] The above description of embodiments of the invention is provided for purposes of description to one of ordinary skill in the related art. It is not intended to be exhaustive or to limit the invention to a single disclosed embodiment. In some instances, well-known components and/or processes have not been described in detail, so as not to obscure the embodiments described herein.

[0241 ] Numerous alternatives and variations to the present invention will be apparent to those skilled in the art of the above teaching. Accordingly, while some alternative embodiments have been discussed specifically, other embodiments will be apparent or relatively easily developed by those of ordinary skill in the art. The invention is intended to embrace all alternatives, modifications, and variations of the present invention that have been discussed herein, and other embodiments that fall within the spirit and scope of the above described invention.

[0242] It is to be particularly noted that, although preferred embodiments of methods and systems as described herein relate to obtaining or providing deposit loans, in alternative aspects and/or embodiments, modified systems and methods as described herein can be applied to obtaining or providing any other suitable type of loan.

[0243] For example, subject to minor modification as will be apparent to the skilled person, methods or systems as described herein may be applied to provision of loans per se, that are not associated with any primary loan. For example, methods or systems as described herein can be applied to obtaining or providing loans for other assets such as car loans and boat loans, etc. The skilled person will understand that in these embodiments, broadly, a car loan, boat loan, or other suitable loan per se can be obtained for and/or provided to a borrower by obtaining a plurality of loan offers from a plurality lenders, each of the plurality of loan offers contributing part of the loan. Such alternatives are explicitly included and encompassed by at least some aspects and embodiments of the invention described herein.

Claims

1. A computational method for obtaining a deposit, including steps of:

matching a plurality of lender profiles corresponding to respective lenders with a deposit loan profile corresponding to a borrower;

connecting the plurality of lenders to the deposit loan profile; and

obtaining deposit loan offers for the deposit loan profile from the plurality of lenders.

2. The method of claim 1 , wherein matching the plurality of lender profiles to the deposit loan profile is performed using a machine learning model.

3. The method of claim 1 or claim 2, including a step of:

comparing a plurality of potential lender profiles to the deposit loan profile, prior to matching the plurality of lender profiles with the deposit loan profile.

4. The method of claim 3, wherein comparing the plurality of potential lender profiles to the deposit loan profile is performed using a machine learning model.

5. The method of any preceding claim, wherein the deposit loan profile includes data on the corresponding borrower selected from primary loan data, desired deposit loan data, and preferred lender data.

6. The method of any preceding claim, wherein the deposit loan profile includes data on the corresponding borrower selected from personal data, social data, income data, asset data, expenditure data, current borrowing data, and previous borrowing data.

7. The method of any preceding claim, wherein the plurality of lender profiles include data on the respective corresponding lender selected from personal data, social data, income data, asset data, expenditure data, current lending data, and previous lending data.

8. The method of any preceding claim, wherein the plurality of lender profiles include data on the respective corresponding lender selected from preferred primary loan data, preferred deposit loan data, and preferred borrower data.

9. The method of any preceding claim, including a step of creating the deposit loan profile, prior to matching the plurality of lender profiles to the deposit loan profile.

10. The method of claim 9, wherein the step of creating the deposit loan profile includes obtaining data on preferred lenders using a machine learning model.

1 1. The method of any preceding claim, including a step of creating one or more of the plurality of lender profiles, prior to matching the plurality of lender profiles to the deposit loan profile.

12. The method of claim 4, including a step of creating one or more of the plurality of potential lender profiles, prior to comparing the plurality of potential lender profiles to the deposit loan profile.

13. The method of claim 1 1 or claim 12, wherein the step of creating the lender profile and/or the potential lender profile includes obtaining data on preferred borrowers using a machine learning model.

14. The method of any preceding claim, wherein the respective deposit loan offers are obtained from each of the lenders subject to a condition selected from deposit loan amount, deposit loan term, deposit loan repayment frequency, and deposit loan interest rate.

15. The method of any preceding claim, including a step of prioritising the deposit loan offers for the deposit loan profile.

16. The method of claim 14, including a step of prioritising the deposit loan offers for the deposit loan profile based, at least on part, on the condition selected from deposit loan amount, deposit loan term, deposit loan repayment frequency, and deposit loan interest rate.

17. The method of any preceding claim, including the step of prioritising the deposit loan offers for the deposit loan profile based, at least in part, on a comparison of the lender profile corresponding to the lender from which the deposit loan offer was made to the deposit loan profile.

18. The method of any preceding claim, including a step of assessing the deposit loan profile, before and/or after matching the plurality of lender profiles to the deposit loan profile.

19. The method of claim 18, wherein the step of assessing the deposit loan profile includes approving the deposit loan profile subject to a condition selected from deposit loan amount, deposit loan term, deposit loan repayment frequency, and deposit loan interest rate.

20. The method of any preceding claim, including a step of evaluating a deposit loan offer for the deposit loan profile obtained from the plurality of lenders.

21. The method of claim 20, wherein the step of evaluating the deposit loan offer includes obtaining a decision on the deposit loan offer from the borrower corresponding to the deposit loan profile.

22. The method of any preceding claim, including a step of transferring one or more of the plurality of deposit loan offers to the deposit loan profile, to thereby obtain the deposit.

23. The method of any preceding claim including a step of obtaining a repayment from the borrower corresponding to the deposit loan profile.

24. The method of any preceding claim including a step of valuing and/or assessing equity of an asset associated with the deposit.

25. The method of claim 22 including a step of transferring the deposit from a first primary loan to a second primary loan.

26. A computing system comprising a processor; and a transmitter and receiver connected to the processor, the computer system being adapted to:

match a plurality of lender profiles corresponding to respective lenders with a deposit loan profile corresponding to a borrower;

connect the plurality of lenders to the deposit loan profile; and

obtain deposit loan offers for the deposit loan profile from the plurality of lenders.

27. The computing system of claim 26, the computer system being adapted to produce, run, and/or update a machine learning model for matching the plurality of lender profiles with the deposit loan profile.

28. The computing system of claim 26 or claim 27, comprising an input component and/or a storage component connected to the processor.

29. The computing system of any one of claims 26-28, for or when used for the method any one of claims 1 -25.