CN114549209A - Intelligent risk assessment method, device, equipment and medium - Google Patents
Intelligent risk assessment method, device, equipment and medium Download PDFInfo
- Publication number
- CN114549209A CN114549209A CN202210178873.6A CN202210178873A CN114549209A CN 114549209 A CN114549209 A CN 114549209A CN 202210178873 A CN202210178873 A CN 202210178873A CN 114549209 A CN114549209 A CN 114549209A
- Authority
- CN
- China
- Prior art keywords
- risk assessment
- index
- target asset
- data
- model
- 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.)
- Pending
Links
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
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application relates to the technical field of data analysis, in particular to an intelligent risk assessment method, device, equipment and medium, which are used for performing risk assessment on target assets according to index data corresponding to position taking information, and can more accurately assess financial risks existing in an asset management process based on the position taking information and index factors, so that management risks are effectively reduced. The method comprises the following steps: acquiring position taken information of a target asset to be evaluated; according to the position taken information of the target asset, determining index data corresponding to a pre-configured index factor, wherein the index factor is used for representing financial risks existing in the asset management process from multiple dimensions; and performing risk assessment on the target asset according to the index data corresponding to the index factors to obtain a risk assessment value corresponding to the target asset.
Description
Technical Field
The present application relates to the field of data analysis technologies, and in particular, to an intelligent risk assessment method, apparatus, device, and medium.
Background
The financial intelligent risk identification system is a management system for performing dimension analysis based on big data and preventing, finding and correcting related risks in time aiming at financial institutions such as banks, securities and the like. In the era of digital economy, the risk recognition capability is becoming an important factor affecting the sustainable development of financial institutions. With the increasing development of financial markets, the investment channels and investment targets of financial assets, such as stocks, bonds, commodity futures, foreign exchange, derivatives, funds, etc., are becoming more abundant. As the number of financial assets rapidly grows, how to accurately conduct risk assessment is a necessary challenge.
At present, risk control mainly aims at monitoring of investment amount, investment proportion and the like with supervision requirements and contract requirements, generally refers to post-investment management, and has weak risk control strength before and during investment and lacks prospective risk prediction. Even if the risk assessment is carried out on the investment target, the risk assessment is rough, and the accuracy is difficult to guarantee.
Disclosure of Invention
The application provides an intelligent risk assessment method, an intelligent risk assessment device, equipment and a medium, which are used for performing risk assessment on target assets according to index data corresponding to position taking information, and can more accurately assess financial risks existing in an asset management process based on the position taking information and index factors, so that management risks are effectively reduced.
In a first aspect, an intelligent risk assessment method provided in an embodiment of the present application includes:
acquiring position taken information of a target asset to be evaluated;
according to the position taken information of the target asset, determining index data corresponding to a pre-configured index factor, wherein the index factor is used for representing financial risks existing in the asset management process from multiple dimensions;
and performing risk assessment on the target asset according to the index data corresponding to the index factors to obtain a risk assessment value corresponding to the target asset.
According to the method, the index factors are configured in advance, the index data corresponding to each index factor are determined according to the position taken information of the target asset, risk assessment of the target asset is carried out based on each index data, the index factors can represent financial risks existing in the asset management process from multiple dimensions, more accurate wind control risks can be provided for fund managers, the financial risks in the management process are reduced, the financial risks of financial institutions can be effectively reduced, and the method has important significance in the field of intelligent wind control.
As an optional implementation, the determining, according to the position taken information of the target asset, the index data corresponding to a preconfigured index factor includes:
acquiring the bin transferring information of a target asset to be evaluated;
and determining index data corresponding to a pre-configured index factor according to the position taking information and the position adjusting information of the target asset.
As an optional implementation manner, the performing risk assessment on the target asset according to the index data corresponding to the index factor to obtain a risk assessment value corresponding to the target asset includes:
and inputting the index data corresponding to the index factors into a pre-trained risk assessment model, and outputting the risk assessment value corresponding to the target asset, wherein the risk assessment model is obtained by training an initial model based on sample index data, and the sample index data is determined based on historical data of each data source and the index factors.
As an optional implementation manner, after obtaining the risk assessment model trained in advance, the method further includes:
carrying out periodic training on the initial model by using sample index data acquired periodically to obtain a periodically updated risk assessment model;
and performing risk assessment by using the periodically updated risk assessment model.
As an optional implementation manner, after obtaining the risk assessment model trained in advance, the method further includes:
updating the preset index factors, and updating the sample index data according to the updated index factors and the historical data of each data source;
and training the initial model by using the updated sample index data to obtain a new risk assessment model, and performing risk assessment by using the new risk assessment model.
As an alternative embodiment, the risk assessment model includes any one of the following:
a random forest model, a clustering model, a logistic regression model, a decision tree model and a support vector machine model.
As an optional implementation, the data sources include any one or more of the following:
the system comprises a research data source, a transaction data source, a clearing data source, a valuation data source and a three-party data source.
As an optional implementation manner, after obtaining the risk assessment value corresponding to the target asset, the method further includes:
displaying an evaluation result according to the risk evaluation value corresponding to the target asset, and performing risk early warning according to a preset rule; and/or the presence of a gas in the gas,
and generating and displaying a risk control report according to the risk assessment value corresponding to the target asset so as to provide an asset management mode for reducing the risk for the user.
As an optional implementation manner, before performing risk assessment on the target asset according to the index data corresponding to the index factor, the method further includes:
removing repeated data in the index data; and/or the presence of a gas in the gas,
and removing dirty data in the index data.
As an alternative embodiment, the target asset to be evaluated includes at least one of a portfolio, and an investment target.
As an optional implementation, the index factor includes at least one of a financial default index, a loss index, and a financial fraud index.
In a second aspect, an intelligent risk assessment device provided in an embodiment of the present application includes:
the position holding unit is used for obtaining position holding information of the target asset to be evaluated;
the index determining unit is used for determining index data corresponding to pre-configured index factors according to the position taken information of the target asset, wherein the index factors are used for representing financial risks existing in the asset management process from multiple dimensions;
and the risk assessment unit is used for performing risk assessment on the target asset according to the index data corresponding to the index factor to obtain a risk assessment value corresponding to the target asset.
As an optional implementation manner, the index determining unit is specifically configured to:
acquiring the bin transferring information of a target asset to be evaluated;
and determining index data corresponding to a pre-configured index factor according to the position taking information and the position adjusting information of the target asset.
As an optional implementation manner, the risk assessment unit is specifically configured to:
and inputting the index data corresponding to the index factors into a pre-trained risk assessment model, and outputting the risk assessment value corresponding to the target asset, wherein the risk assessment model is obtained by training an initial model based on sample index data, and the sample index data is determined based on historical data of each data source and the index factors.
As an optional implementation manner, after obtaining the pre-trained risk assessment model, the method further includes a period updating unit for:
carrying out periodic training on the initial model by using sample index data acquired periodically to obtain a periodically updated risk assessment model;
and performing risk assessment by using the periodically updated risk assessment model.
As an optional implementation manner, after obtaining the risk assessment model trained in advance, the method further includes an index updating unit, configured to:
updating the preset index factors, and updating the sample index data according to the updated index factors and the historical data of each data source;
and training the initial model by using the updated sample index data to obtain a new risk assessment model, and performing risk assessment by using the new risk assessment model.
As an alternative embodiment, the risk assessment model includes any one of the following:
a random forest model, a clustering model, a logistic regression model, a decision tree model and a support vector machine model.
As an optional implementation, the data sources include any one or more of the following:
the system comprises a research data source, a transaction data source, a clearing data source, a valuation data source and a three-party data source.
As an optional implementation manner, after obtaining the risk assessment value corresponding to the target asset, the method further includes a result presentation unit, configured to:
displaying an evaluation result according to the risk evaluation value corresponding to the target asset, and performing risk early warning according to a preset rule; and/or the presence of a gas in the gas,
and generating and displaying a risk control report according to the risk assessment value corresponding to the target asset so as to provide an asset management mode for reducing the risk for the user.
As an optional implementation manner, before performing risk assessment on the target asset according to the index data corresponding to the index factor, the system further includes a cleaning data unit configured to:
removing repeated data in the index data; and/or the presence of a gas in the gas,
and removing dirty data in the index data.
As an alternative embodiment, the target asset to be evaluated includes at least one of an investment portfolio and an investment target.
As an optional implementation, the index factor includes at least one of a financial default index, a loss index, and a financial fraud index.
In a third aspect, an embodiment of the present application further provides an electronic device, including:
a memory for storing program instructions;
the processor is used for calling the program instructions stored in the memory and executing the following steps according to the obtained program instructions:
acquiring position taken information of a target asset to be evaluated;
according to the position taken information of the target asset, determining index data corresponding to a pre-configured index factor, wherein the index factor is used for representing financial risks existing in the asset management process from multiple dimensions;
and performing risk assessment on the target asset according to the index data corresponding to the index factors to obtain a risk assessment value corresponding to the target asset.
As an alternative embodiment, the processor is configured to perform:
acquiring the bin transferring information of a target asset to be evaluated;
and determining index data corresponding to a pre-configured index factor according to the position taking information and the position adjusting information of the target asset.
As an alternative embodiment, the processor is configured to perform:
and inputting the index data corresponding to the index factors into a pre-trained risk assessment model, and outputting the risk assessment value corresponding to the target asset, wherein the risk assessment model is obtained by training an initial model based on sample index data, and the sample index data is determined based on historical data of each data source and the index factors.
As an optional implementation manner, after obtaining the pre-trained risk assessment model, the processor is specifically further configured to perform:
carrying out periodic training on the initial model by using sample index data acquired periodically to obtain a periodically updated risk assessment model;
and performing risk assessment by using the periodically updated risk assessment model.
As an optional implementation manner, after obtaining the pre-trained risk assessment model, the processor is specifically further configured to perform:
updating the preset index factors, and updating the sample index data according to the updated index factors and the historical data of each data source;
and training the initial model by using the updated sample index data to obtain a new risk assessment model, and performing risk assessment by using the new risk assessment model.
As an alternative embodiment, the risk assessment model includes any one of the following:
a random forest model, a clustering model, a logistic regression model, a decision tree model and a support vector machine model.
As an optional implementation, the data sources include any one or more of the following:
the system comprises a research data source, a transaction data source, a clearing data source, a valuation data source and a three-party data source.
As an optional implementation manner, after obtaining the risk assessment value corresponding to the target asset, the processor is further specifically configured to perform:
displaying an evaluation result according to the risk evaluation value corresponding to the target asset, and performing risk early warning according to a preset rule; and/or the presence of a gas in the atmosphere,
and generating and displaying a risk control report according to the risk assessment value corresponding to the target asset so as to provide an asset management mode for reducing the risk for the user.
As an optional implementation manner, before performing risk assessment on the target asset according to the index data corresponding to the index factor, the processor is further specifically configured to perform:
removing repeated data in the index data; and/or the presence of a gas in the gas,
and removing dirty data in the index data.
As an alternative embodiment, the target asset to be evaluated includes at least one of a portfolio, and an investment target.
As an optional implementation, the index factor includes at least one of a financial default index, a loss index, and a financial fraud index.
In a fourth aspect, the present embodiments also provide a computer-readable storage medium, in which a computer program is stored, the computer program comprising program instructions that, when executed by a computer, cause the computer to perform the steps of the method of the first aspect.
In a fifth aspect, an embodiment of the present application further provides a computer program product, where the computer program product includes: computer program code for causing a computer to perform the steps of the method according to the first aspect described above, when said computer program code is run on a computer.
These and other aspects of the present application will be more readily apparent from the following description of the embodiments.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a flowchart of an implementation of an intelligent risk assessment method according to an embodiment of the present disclosure;
fig. 2 is a flowchart of an implementation of an intelligent risk assessment method based on machine learning according to an embodiment of the present application;
fig. 3 is a schematic diagram of an intelligent risk assessment apparatus according to an embodiment of the present application;
fig. 4 is a schematic diagram of an intelligent risk assessment device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions in the embodiments of the present application will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application. In the present application, the embodiments and features of the embodiments may be arbitrarily combined with each other without conflict. Also, while a logical order is shown in the flow diagrams, in some cases, the steps shown or described may be performed in an order different than here.
The terms "first" and "second" in the description and claims of the present application and the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the term "comprises" and any variations thereof, which are intended to cover non-exclusive protection. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus. The "plurality" in the present application may mean at least two, for example, two, three or more, and the embodiments of the present application are not limited.
In the technical scheme, the data acquisition, transmission, use and the like all meet the requirements of relevant national laws and regulations.
Embodiment 1, before describing an intelligent risk assessment method provided in the embodiments of the present application, for easy understanding, the following technical background of the embodiments of the present application is first described in detail.
The financial intelligent risk identification system is a management system for timely preventing, finding and correcting related risks by dimension analysis of mass data aiming at financial institutions such as banks, securities and the like. In the era of digital economy, the risk recognition capability is becoming an important factor affecting the sustainable development of financial institutions. Effectively deal with the new form of financial service, traditional financial institution vigorously carries out intelligent wind-control construction and is imperative. With the increasing development of financial markets, the investment channels and investment targets for financial assets, such as stocks, bonds, commodity futures, foreign exchanges, derivatives, funds, etc., have become increasingly abundant. Along with the quantity of financial assets increases fast, how timely prevent, discover, correct relevant risk is the challenge that must face, and this application aims at introducing new technologies such as artificial intelligence, cloud computing and big data, integrates inside and outside resources, builds brand-new intelligent wind control system, puts through each link such as preceding, well as back, fund, product, constantly realizes full risk intelligence management and control, and comprehensive helping hand risk management level promotes. The traditional wind control system is mainly used for fixed and regular risk control, and usually makes proportional limits on the scale of an investment portfolio, the range of an investment target, the amount of the investment target and the like according to the requirements of a supervision department and contract requirements, and the made wind control indexes have hysteresis, so that the potential risks of the investment target and the investment portfolio cannot be predicted. At present, in the market, there are few systems for risk identification and assessment for investment portfolio level, and the assessment accuracy is not high, most systems are for assessment of an investment target, for example, for assessment of future income and risk of a certain stock, and the assessment mode is rough. Therefore, for financial wind control services, it is imperative to design a wind control system with predictability and intellectualization.
According to the intelligent risk assessment method, index factors are configured in advance, index data corresponding to each index factor are determined according to the position taken information of target assets, risk assessment of the target assets is conducted based on each index data, the index factors can represent financial risks existing in the asset management process from multiple dimensions, more accurate wind control risks can be provided for fund managers, the financial risks in the management process are reduced, financial risks of financial institutions can be effectively reduced, and the method has important significance in the field of intelligent wind control. The financial risk of the target asset can be evaluated based on the position taking information and the index data of the target asset, the target asset is likely to suffer from the influences of card stopping, market returning and the like in the management process, and great financial risk is easily brought to a financial institution.
As shown in fig. 1, the implementation flow of the intelligent risk assessment method provided by this embodiment is as follows:
in some embodiments, the target assets in the present embodiment include, but are not limited to, at least one of portfolios, investment targets. Where an investment portfolio may represent a portfolio of multiple asset units, an investment target may represent an asset unit, such as a single stock.
Wherein, the investment target refers to an object pointed by the common rights and obligations of both parties in the investment contract; investment targets include, but are not limited to: stocks, precious metals, bonds, funds, and other financial derivatives. A portfolio refers to a collection of stocks, bonds, financial derivatives, etc., held by an investor or financial institution.
Taken in position in this embodiment means that the investor holds a futures contract before the physical delivery or cash delivery expires. The position taken information in this embodiment includes, but is not limited to, the movement and position taken proportion of the target asset, for example, the movement and position taken proportion of the dominant asset in the target asset.
In some embodiments, the position taken information for the target asset that the fund management user is managing may be obtained based on the authorization information of the fund management user.
in some embodiments, the present embodiment pre-configures a plurality of different dimensional indicator factors, including but not limited to at least a plurality of financial default indicators, loss indicators, financial fraud indicators. Optionally, the index factor in this embodiment may further include a special index configured by the management user, for example, the management user configures a corresponding special index for the position taken information of the target asset according to a critical index related to the industry, so that the risk assessment is more professional and accurate.
In some embodiments, the indicator factor is a financial default indicator, including but not limited to card stopping information, market information, and the like, that has a default risk. When the index factor is a loss index, the index factor includes, but is not limited to, information with loss risk, such as market withdrawal information, market share, liquidity, and the like. When the index factor is a financial fraud index, the index factor includes but is not limited to information with financial fraud characteristics, such as double-high information of deposit and loan, abnormal information of inventory turnover rate, sufficient cash flow rate, customer rating (such as customer rating based on internal system of bank), abnormal information of fund traffic, and related information of fund traffic.
Optionally, the index factor in this embodiment may further include: the proportion of deposits to total equity, the proportion of loans to total equity, the equity rate, the receivable account age, the cash flow sufficiency rate, the flow rate, and the like. The index factor in this embodiment may be defined according to the industry property and the actual requirement, which is not limited too much in this embodiment.
In the implementation, according to the position taken information of the target asset and the pre-configured index factor, the index data related to the index factor in the position taken information is determined, the index data is used as an evaluation index for evaluating the target asset, and corresponding risk assessment is carried out on the target asset.
And 102, performing risk assessment on the target asset according to the index data corresponding to the index factors to obtain a risk assessment value corresponding to the target asset.
In some embodiments, before performing risk assessment on the target asset according to the indicator data corresponding to the indicator factor, the method further includes:
removing repeated data in the index data; and/or removing dirty data in the index data.
Before risk assessment is performed by using the index data, the index data can be cleaned, repeated data and dirty data are removed, and effectiveness and accuracy of the risk assessment are further improved.
In some embodiments, the risk assessment may be performed on the target asset based on the index data by using a machine learning model, or may be performed on the target asset based on the index data by using other algorithms, which is not limited in this embodiment.
In some embodiments, the present embodiment further provides a method for determining index data, which is specifically as follows:
firstly, acquiring the shunting information of a target asset to be evaluated; in practice, the adjustment of the stock refers to that some stocks held by investors are sold completely or a part of the stocks is sold and replaced by other stocks. The binning information includes, but is not limited to, binning information.
And secondly, determining index data corresponding to a pre-configured index factor according to the position taking information and the position adjusting information of the target asset. In the implementation, the position taking information and position adjusting information of the target asset are utilized, the holding and adjusting conditions of the target asset in the management process can be accurately captured, and important evaluation indexes are provided for more accurately estimating risks.
In implementation, the index data matched with the index factors can be determined from the position taking information and the position adjusting information of the target assets and the index factors.
In some embodiments, after the index data corresponding to the target asset is determined by the method, risk assessment is performed based on big data and a machine learning model, and the specific implementation manner is as follows:
inputting the index data corresponding to the index factors into a pre-trained risk assessment model, and outputting a risk assessment value corresponding to the target asset;
the risk assessment model is obtained by training an initial model based on sample index data, and the sample index data is determined based on historical data of each data source and the index factor.
In some embodiments, the risk assessment value may be a normalized value, such as a value of 0-100, with a larger value indicating a higher risk and a smaller value indicating a lower risk. It should be noted that the risk index value in this embodiment not only represents the profit risk, but also represents the default risk, the fund management risk, the financial fraud risk, and the like, and can perform risk assessment from multiple dimensions, thereby improving the accuracy and comprehensiveness of the risk assessment.
In some embodiments, the risk assessment model in this embodiment includes any of:
a random forest model, a clustering model, a logistic regression model, a decision tree model and a support vector machine model.
In the process of training the risk assessment model, sample index data for training needs to be obtained first, and in implementation, the sample index data is determined based on historical data of each data source and the index factors. And calculating index data corresponding to each index factor from the historical data, taking the calculated index data as sample index data, and training the initial model by using the sample index data to obtain a finally trained risk assessment model.
In some embodiments, the data source of this embodiment is one or more, including any one or any more of the following: the system comprises a research data source, a transaction data source, a clearing data source, a valuation data source and a three-party data source. Wherein a three-party data source represents a third-party data source, such as wangde, money, etc.
In some embodiments, after each data source is acquired, data cleansing is first performed on the data in each data source, including but not limited to removing duplicate data, and/or removing dirty data. The dirty data refers to that data in the source system is not in a given range or has no meaning for actual service, or the data format is illegal, and irregular coding and ambiguous service logic exist in the source system. And then, determining corresponding index data by using the cleaned data source and a pre-configured index factor, and training the initial model by using the index data as sample index data.
In some embodiments, the cleaned data source may be written into a data warehouse and stored, and optionally, the data warehouse performs data layering based on Hive (a data warehouse tool based on Hadoop for data extraction, transformation, and loading), and the Spark (a fast general-purpose computing engine designed for large-scale data processing) is used as a computing engine, which may provide data for the entire system.
In some embodiments, the risk assessment model in this embodiment is periodically updated, and since the financial industry has periodicity, this embodiment performs periodic training on the initial model by using sample index data obtained periodically to obtain a periodically updated risk assessment model; and performing risk assessment by using the periodically updated risk assessment model. Optionally, the period in this embodiment may be determined according to an iteration period of the financial industry corresponding to the target asset, the iteration period corresponding to the target asset may be used as an updated period, and the risk assessment model is executed according to the iteration period, which is not limited in this embodiment.
In some embodiments, the present embodiment may further dynamically adjust the configured index factor, and in implementation, the preconfigured index factor is updated, and the sample index data is updated according to the updated index factor and the historical data of each data source; and training the initial model by using the updated sample index data to obtain a new risk assessment model, and performing risk assessment by using the new risk assessment model.
Optionally, the updating manner of the index factor in this embodiment includes, but is not limited to: at least one of modify, add, delete.
In some embodiments, the embodiment may further provide a visual interface, and the user displays the risk assessment result to the user, and performs risk early warning according to a certain rule, so as to improve the use experience of the user. In practice, the risk result presentation is performed by any of the following means:
mode 1) displaying an evaluation result according to the risk evaluation value corresponding to the target asset, and carrying out risk early warning according to a preset rule;
in implementation, the evaluation results corresponding to different risk levels can be displayed to the user according to the interval where the risk evaluation value is located and the risk level corresponding to the interval, and corresponding risk early warning is performed. For example, when the risk level corresponding to the risk assessment value is high risk, a screen corresponding to the high risk is displayed to the user, and an early warning prompt corresponding to the high risk is performed, such as an audio early warning prompt.
Mode 2) according to the risk assessment value corresponding to the target asset, generating and displaying a risk control report so as to provide an asset management mode for reducing risks for users.
In practice, the generated risk control report includes information such as management methods and measures to instruct the management user how to perform risk control.
And 3) generating and displaying a risk control report according to the risk assessment value corresponding to the target asset, displaying an assessment result, and performing risk early warning according to a preset rule.
In some embodiments, as shown in fig. 2, the present embodiment further provides an intelligent risk assessment method based on machine learning, and the specific implementation flow of the method is as follows:
200, removing repeated data and dirty data from the historical data of each data source, and determining sample index data based on the removed historical data of the data source and a preset index factor;
optionally, each data source includes any one or more of the following: the system comprises a research data source, a transaction data source, a clearing data source, a valuation data source and a three-party data source.
202, acquiring position taking information of a target asset to be evaluated, and determining index data corresponding to a pre-configured index factor according to the position taking information of the target asset;
optionally, acquiring the bin transferring information of the target asset to be evaluated; and determining index data corresponding to a pre-configured index factor according to the position taking information and the position adjusting information of the target asset.
and 204, generating and displaying a risk control report according to the risk assessment value corresponding to the target asset, displaying an assessment result, and performing risk early warning according to a preset rule.
Embodiment 2, based on the same inventive concept, the embodiment of the present application further provides an intelligent risk assessment apparatus, and since the device is a device in the method in the embodiment of the present application, and the principle of the device to solve the problem is similar to that of the method, the implementation of the device may refer to the implementation of the method, and repeated parts are not described again.
As shown in fig. 3, the apparatus includes:
the position taking unit 300 is used for obtaining position taking information of the target asset to be evaluated;
an index determining unit 301, configured to determine index data corresponding to preconfigured index factors according to the position taken information of the target asset, where the index factors are used for characterizing financial risks existing in the asset management process from multiple dimensions;
and a risk assessment unit 302, configured to perform risk assessment on the target asset according to the index data corresponding to the index factor, so as to obtain a risk assessment value corresponding to the target asset.
As an optional implementation manner, the index determining unit 301 is specifically configured to:
acquiring the bin transferring information of a target asset to be evaluated;
and determining index data corresponding to a pre-configured index factor according to the position taking information and the position adjusting information of the target asset.
As an optional implementation manner, the risk assessment unit 302 is specifically configured to:
and inputting the index data corresponding to the index factors into a pre-trained risk assessment model, and outputting the risk assessment value corresponding to the target asset, wherein the risk assessment model is obtained by training an initial model based on sample index data, and the sample index data is determined based on historical data of each data source and the index factors.
As an optional implementation manner, after obtaining the pre-trained risk assessment model, the method further includes a period updating unit for:
carrying out periodic training on the initial model by using sample index data acquired periodically to obtain a periodically updated risk assessment model;
and performing risk assessment by using the periodically updated risk assessment model.
As an optional implementation manner, after obtaining the risk assessment model trained in advance, the method further includes an index updating unit, configured to:
updating the preset index factors, and updating the sample index data according to the updated index factors and the historical data of each data source;
and training the initial model by using the updated sample index data to obtain a new risk assessment model, and performing risk assessment by using the new risk assessment model.
As an alternative embodiment, the risk assessment model includes any one of the following:
a random forest model, a clustering model, a logistic regression model, a decision tree model and a support vector machine model.
As an optional implementation, the data sources include any one or more of the following:
the system comprises a research data source, a transaction data source, a clearing data source, a valuation data source and a three-party data source.
As an optional implementation manner, after obtaining the risk assessment value corresponding to the target asset, the method further includes a result presentation unit, configured to:
displaying an evaluation result according to the risk evaluation value corresponding to the target asset, and performing risk early warning according to a preset rule; and/or the presence of a gas in the gas,
and generating and displaying a risk control report according to the risk assessment value corresponding to the target asset so as to provide an asset management mode for reducing the risk for the user.
As an optional implementation manner, before performing risk assessment on the target asset according to the index data corresponding to the index factor, the system further includes a cleaning data unit configured to:
removing repeated data in the index data; and/or the presence of a gas in the gas,
and removing dirty data in the index data.
As an alternative embodiment, the target asset to be evaluated includes at least one of a portfolio, and an investment target.
As an optional implementation, the index factor includes at least one of a financial default index, a loss index, and a financial fraud index.
Embodiment 3, based on the same inventive concept, the embodiment of the present application further provides an electronic device, and since the device is a device in the method in the embodiment of the present application, and the principle of the device to solve the problem is similar to that of the method, the implementation of the device may refer to the implementation of the method, and repeated details are omitted.
As shown in fig. 4, the electronic apparatus includes:
a memory 400 for storing program instructions;
a processor 401, configured to call the program instruction stored in the memory 400, and execute the following steps according to the obtained program instruction:
acquiring position taken information of a target asset to be evaluated;
according to the position taken information of the target asset, determining index data corresponding to a pre-configured index factor, wherein the index factor is used for representing financial risks existing in the asset management process from multiple dimensions;
and performing risk assessment on the target asset according to the index data corresponding to the index factors to obtain a risk assessment value corresponding to the target asset.
As an optional implementation, the processor 401 is specifically configured to perform:
acquiring the bin transferring information of a target asset to be evaluated;
and determining index data corresponding to a pre-configured index factor according to the position taking information and the position adjusting information of the target asset.
As an optional implementation, the processor 401 is specifically configured to perform:
and inputting the index data corresponding to the index factors into a pre-trained risk assessment model, and outputting the risk assessment value corresponding to the target asset, wherein the risk assessment model is obtained by training an initial model based on sample index data, and the sample index data is determined based on historical data of each data source and the index factors.
As an optional implementation, after obtaining the pre-trained risk assessment model, the processor 401 is further specifically configured to perform:
carrying out periodic training on the initial model by using sample index data acquired periodically to obtain a periodically updated risk assessment model;
and performing risk assessment by using the periodically updated risk assessment model.
As an optional implementation, after obtaining the pre-trained risk assessment model, the processor 401 is further specifically configured to perform:
updating the preset index factors, and updating the sample index data according to the updated index factors and the historical data of each data source;
and training the initial model by using the updated sample index data to obtain a new risk assessment model, and performing risk assessment by using the new risk assessment model.
As an alternative embodiment, the risk assessment model includes any one of the following:
a random forest model, a clustering model, a logistic regression model, a decision tree model and a support vector machine model.
As an optional implementation, the data sources include any one or more of the following:
the system comprises a research data source, a transaction data source, a clearing data source, a valuation data source and a three-party data source.
As an optional implementation manner, after obtaining the risk assessment value corresponding to the target asset, the processor 401 is further specifically configured to perform:
displaying an evaluation result according to the risk evaluation value corresponding to the target asset, and performing risk early warning according to a preset rule; and/or the presence of a gas in the gas,
and generating and displaying a risk control report according to the risk assessment value corresponding to the target asset so as to provide an asset management mode for reducing the risk for the user.
As an optional implementation manner, before performing risk assessment on the target asset according to the index data corresponding to the index factor, the processor 401 is further specifically configured to perform:
removing repeated data in the index data; and/or the presence of a gas in the gas,
and removing dirty data in the index data.
As an alternative embodiment, the target asset to be evaluated includes at least one of a portfolio, and an investment target.
As an optional implementation, the index factor includes at least one of a financial default index, a loss index, and a financial fraud index.
Based on the same inventive concept, the embodiments of the present application further provide a computer-readable storage medium storing a computer program, the computer program comprising program instructions that, when executed by a computer, cause the computer to perform the steps of:
acquiring position taken information of a target asset to be evaluated;
according to the position taken information of the target asset, determining index data corresponding to a pre-configured index factor, wherein the index factor is used for representing financial risks existing in the asset management process from multiple dimensions;
and performing risk assessment on the target asset according to the index data corresponding to the index factor to obtain a risk assessment value corresponding to the target asset.
Based on the same inventive concept, the embodiment of the present application further provides a computer program product, where the computer program product includes: computer program code which, when run on a computer, causes the computer to perform the steps of:
acquiring position taken information of a target asset to be evaluated;
according to the position taken information of the target asset, determining index data corresponding to a pre-configured index factor, wherein the index factor is used for representing financial risks existing in the asset management process from multiple dimensions;
and performing risk assessment on the target asset according to the index data corresponding to the index factors to obtain a risk assessment value corresponding to the target asset.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (15)
1. An intelligent risk assessment method, the method comprising:
acquiring position taken information of a target asset to be evaluated;
according to the position taken information of the target asset, determining index data corresponding to a pre-configured index factor, wherein the index factor is used for representing financial risks existing in the asset management process from multiple dimensions;
and performing risk assessment on the target asset according to the index data corresponding to the index factors to obtain a risk assessment value corresponding to the target asset.
2. The method of claim 1, wherein determining metric data corresponding to a preconfigured metric factor based on the position taken information for the target asset comprises:
acquiring the bin transferring information of a target asset to be evaluated;
and determining index data corresponding to a pre-configured index factor according to the position taking information and the position adjusting information of the target asset.
3. The method of claim 1, wherein the performing risk assessment on the target asset according to the index data corresponding to the index factor to obtain a risk assessment value corresponding to the target asset comprises:
and inputting the index data corresponding to the index factors into a pre-trained risk assessment model, and outputting the risk assessment value corresponding to the target asset, wherein the risk assessment model is obtained by training an initial model based on sample index data, and the sample index data is determined based on historical data of each data source and the index factors.
4. The method of claim 3, wherein after obtaining the pre-trained risk assessment model, further comprising:
carrying out periodic training on the initial model by using sample index data acquired periodically to obtain a periodically updated risk assessment model;
and performing risk assessment by using the periodically updated risk assessment model.
5. The method of claim 3, wherein after obtaining the pre-trained risk assessment model, further comprising:
updating the preset index factors, and updating the sample index data according to the updated index factors and the historical data of each data source;
and training the initial model by using the updated sample index data to obtain a new risk assessment model, and performing risk assessment by using the new risk assessment model.
6. The method of claim 3, wherein the risk assessment model comprises any one of:
a random forest model, a clustering model, a logistic regression model, a decision tree model and a support vector machine model.
7. The method of claim 3, wherein the respective data sources include any one or more of:
the system comprises a research data source, a transaction data source, a clearing data source, a valuation data source and a three-party data source.
8. The method of claim 1, wherein after obtaining the risk assessment value corresponding to the target asset, further comprising:
displaying an evaluation result according to the risk evaluation value corresponding to the target asset, and performing risk early warning according to a preset rule; and/or the presence of a gas in the gas,
and generating and displaying a risk control report according to the risk assessment value corresponding to the target asset so as to provide an asset management mode for reducing the risk for the user.
9. The method of claim 1, wherein before performing risk assessment on the target asset according to the indicator data corresponding to the indicator factor, the method further comprises:
removing repeated data in the index data; and/or the presence of a gas in the gas,
and removing dirty data in the index data.
10. The method according to any one of claims 1 to 9, wherein the target assets to be evaluated comprise at least one of investment portfolios and investment targets.
11. The method of any of claims 1 to 9, wherein the indicator factors include at least one of financial default indicators, loss indicators, financial fraud indicators.
12. An intelligent risk assessment device, comprising:
the position holding unit is used for obtaining position holding information of the target asset to be evaluated;
the index determining unit is used for determining index data corresponding to pre-configured index factors according to the position taken information of the target asset, wherein the index factors are used for representing financial risks existing in the asset management process from multiple dimensions;
and the risk assessment unit is used for performing risk assessment on the target asset according to the index data corresponding to the index factor to obtain a risk assessment value corresponding to the target asset.
13. An electronic device, comprising:
a memory for storing program instructions;
a processor for calling the program instructions stored in the memory and executing the steps included in the method of any one of claims 1 to 11 according to the obtained program instructions.
14. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program comprising program instructions which, when executed by a computer, cause the computer to carry out the method according to any one of claims 1 to 11.
15. A computer program product, the computer program product comprising: computer program code which, when run on a computer, causes the computer to perform the method of any of the preceding claims 1 to 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210178873.6A CN114549209A (en) | 2022-02-25 | 2022-02-25 | Intelligent risk assessment method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210178873.6A CN114549209A (en) | 2022-02-25 | 2022-02-25 | Intelligent risk assessment method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114549209A true CN114549209A (en) | 2022-05-27 |
Family
ID=81679301
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210178873.6A Pending CN114549209A (en) | 2022-02-25 | 2022-02-25 | Intelligent risk assessment method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114549209A (en) |
-
2022
- 2022-02-25 CN CN202210178873.6A patent/CN114549209A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020143341A1 (en) | Blockchain architecture-based warehouse receipt pledge financing assessment method and device | |
| WO2020143344A1 (en) | Method and device for warehouse receipt pledge financing based on blockchain architecture | |
| KR102009309B1 (en) | Management automation system for financial products and management automation method using the same | |
| CN106651190A (en) | Enterprise risk level assessment method and system | |
| Höglund | Tax payment default prediction using genetic algorithm-based variable selection | |
| US20220351207A1 (en) | System and method for optimization of fraud detection model | |
| CN111583033A (en) | Association analysis method and device based on relation between listed company and stockholder | |
| CN113609193A (en) | Method and device for training prediction model for predicting customer transaction behavior | |
| CN111353901A (en) | Risk identification monitoring method and device and electronic equipment | |
| CN113052705A (en) | Supply chain financial service process management method and device | |
| CN102496126A (en) | Custody asset transaction data monitoring equipment | |
| Coyle et al. | What is the value of data? A review of empirical methods | |
| CN114997975A (en) | Abnormal enterprise identification method, device, equipment, medium and product | |
| CN113449010A (en) | Investment institution income information mining method and device, electronic equipment and storage medium | |
| CN115689713A (en) | Abnormal risk data processing method and device, computer equipment and storage medium | |
| CN116934131A (en) | Enterprise operation condition assessment method, device and equipment | |
| CN113469818B (en) | Investment risk early warning method and device, electronic equipment and computer readable medium | |
| CN115907947A (en) | Enterprise loan risk prediction method and system | |
| CN114549209A (en) | Intelligent risk assessment method, device, equipment and medium | |
| CN117252677A (en) | Credit line determination method and device, electronic equipment and storage medium | |
| CN114418776A (en) | Data processing method, device, terminal equipment and medium | |
| CN114757754A (en) | Image system, method, storage medium and electronic device for listed company | |
| CN112634048A (en) | Anti-money laundering model training method and device | |
| CN114880369A (en) | Risk credit granting method and system based on weak data technology | |
| CN112053217A (en) | Financial valuation statement generation method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |