CN113256121A - Artificial intelligent money laundering method and system - Google Patents
Artificial intelligent money laundering method and system Download PDFInfo
- Publication number
- CN113256121A CN113256121A CN202110580253.0A CN202110580253A CN113256121A CN 113256121 A CN113256121 A CN 113256121A CN 202110580253 A CN202110580253 A CN 202110580253A CN 113256121 A CN113256121 A CN 113256121A
- Authority
- CN
- China
- Prior art keywords
- risk
- account
- data
- money laundering
- rating
- 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
- 238000004900 laundering Methods 0.000 title claims abstract description 121
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000004364 calculation method Methods 0.000 claims abstract description 27
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 22
- 238000012544 monitoring process Methods 0.000 claims abstract description 17
- 238000011156 evaluation Methods 0.000 claims description 13
- 230000002159 abnormal effect Effects 0.000 claims description 11
- 238000007726 management method Methods 0.000 claims description 8
- 238000012550 audit Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 6
- 238000011867 re-evaluation Methods 0.000 description 6
- 239000003814 drug Substances 0.000 description 3
- 229940079593 drug Drugs 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012800 visualization Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000002955 isolation Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 208000001613 Gambling Diseases 0.000 description 1
- 102000056548 Member 3 Solute Carrier Family 12 Human genes 0.000 description 1
- 108091006623 SLC12A3 Proteins 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000013474 audit trail Methods 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Finance (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides an artificial intelligence anti-money laundering method, which specifically comprises the following steps: monitoring the accessed transaction, and acquiring and correlating an account and transaction data; the method comprises the following steps of dividing account types into individual accounts and legal accounts, and classifying transactions according to transaction types; importing the account and transaction data into a risk scoring module for risk scoring, and establishing a risk insight scoring system of an admission link and a transaction link; the account with higher risk level and the transaction are imported into an anti-money laundering decision center for analysis and calculation, and an account relation model is established; for the account with higher risk level, substituting the transaction data into the money laundering model according to the transaction type and the account type to calculate the goodness of fit, and finding the model with the best goodness of fit; checking and data reporting are carried out on the account with higher risk level, the transaction and the goodness-of-fit result; and visually displaying the account relation, the multi-dimensional business situation and the money laundering risk.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an artificial intelligence anti-money laundering method and an artificial intelligence anti-money laundering system.
Background
Money laundering in the modern sense refers to the act of masking and hiding the source and nature of money by financial institutions in various ways from the drug crime, organization crimes of black social nature, terrorist activity crimes, smuggling crimes, bribery crimes, financial management order destruction crimes, financial fraud crimes and the generated income, so that the money laundering is legalized in form.
Money laundering has extremely serious economic, safety, and social consequences. Money laundering provides a motivation for the operation and development of drug vendors, terrorists, illegal weapon traders, corrupt government officials, and other criminals. Money laundering has become more and more international and financial problems associated with criminal activities have become increasingly complicated by the day-to-day advances in technology and globalization of the financial services industry. According to international monetary fund organizations, illegal money laundering worldwide accounts for approximately 2% to 5% of the total domestic production value in the world, between 6000 billion and 1.8 trillion dollars per year, and is increasing in the amount of 1000 billion dollars per year. Especially in the current situation of global economy and internationalization of capital movement, money laundering activities are extremely harmful to the safety of the international financial system and to the international political economic order.
The money laundering scenes comprise network gambling, drug crime, bribery, smuggling crime, tax evasion, financial fraud, terrorist collection, underground money and the like. The money washing identification point has abnormal account opening (different places, agents, false information, online banking without limit and the like), abnormal transaction time (sensitive time, weekend transaction), abnormal transaction amount (huge accumulated amount, specific amount, completeness, limitation, multi-currency transaction and the like), abnormal transaction place, equipment, IP and the like (different places, cross-border, cross-line, off-line IP, high-risk provinces and the like), account short-time frequent transfer and fast forward, account centralized remittance and dispersed remittance and separated transfer, abnormal association of account, equipment and IP, and silent account suddenly has accumulated large-amount transaction and frequent transaction; heuristics, intermittent transactions, no or little remaining balance, more cash or consumption scenario transactions, no cost, etc. But for different money laundering scenarios, it can be generally divided into three phases: a disposal stage, an isolation stage, and a fusion stage.
The treatment stage comprises the following steps: the process of putting criminal profits into the "cleaning system". It is the first stage of money laundering, and is the most easily discovered stage. For example, the criminal income is deposited into banks or converted into bank bills, treasures, credit agencies, etc.; converting a small amount of small denomination cash into a large denomination cash; splitting the large-amount transaction into a plurality of small-amount transactions; buying money orders, insurance or stock, etc.
(II) an isolation stage: through complex financial transactions, criminal revenues are separated from their sources, confounding audit trails and hiding the process of criminal identity.
(III) fusion stage: also known as the "integration phase," is the final phase of money laundering, visually described as "spin-drying," a process that provides surface legitimacy for criminal revenues. For different money laundering scenes, different money laundering models can be established by a deep learning method according to transaction characteristic data.
Disclosure of Invention
Based on the problems proposed in the background art, the invention provides an artificial intelligence anti-money laundering method, which specifically comprises the following steps:
monitoring the accessed transaction, acquiring account and transaction data and associating the account and the transaction data to obtain associated data;
the method comprises the following steps of dividing account types into a personal account and a legal account, and classifying transactions to obtain different transaction types;
importing the associated data into a risk scoring model for risk scoring, and if the score is higher than a preset risk threshold value, determining the associated data as an initial risk account;
based on the transaction type and the account type, transaction data of an initial risk account is input into an anti-money laundering decision center to calculate goodness of fit with all money laundering models, a money laundering model with the best goodness of fit is found out, if the maximum goodness of fit is higher than a preset threshold value, the initial risk account is a risk account, wherein the anti-money laundering decision center comprises at least two money laundering models.
Preferably, the step of importing the associated data into a risk scoring model for risk scoring, and if the score is higher than a preset risk threshold, the associated data is an initial risk account, includes the following steps:
acquiring anti-money laundering business data and anti-money laundering derivative data, wherein the anti-money laundering business data and the anti-money laundering derivative data belong to associated data;
inputting the two types of data into a risk rating model for risk rating calculation to obtain a risk rating result;
and associating the risk rating result with a rating object, adding the risk rating result into a rating object list, setting a risk threshold value based on the rating object list, performing initial evaluation on the risk rating result according to a rating model based on the risk threshold value to obtain an initial risk account, wherein the rating result list is updated according to the risk rating result, and the rating model is optimized according to the rating result.
Preferably, the risk rating calculation comprises an index calculation and a feature calculation;
the indexes comprise basic indexes, attribute indexes and associated indexes; the characteristics comprise transaction characteristics, risk characteristics and early warning characteristics;
the index calculation and the feature calculation specifically include the following processes:
performing index classification on the anti-money laundering business data and the anti-money laundering derivative data according to an index classification rule in the rating index management to obtain a classification result;
combining the classification results into risk sub-items pairwise, and calculating the risk sub-items according to a first weight rule to obtain risk factors, wherein the first weight rule is a weight ratio rule preset according to the influence degree of the index classification results;
calculating the risk factors according to a second weight rule to obtain a risk rating score, wherein the second weight rule is a weight ratio rule preset according to the influence degree of the risk factors;
and converting the risk rating score into a risk grade according to the grading grade conversion matrix.
Preferably, the initial evaluation operation comprises customer identification, KYC audit, due diligence investigation and risk level adjustment.
Preferably, the rating model comprises an admission rating model and a behavior rating model, and the parameters of the admission rating model comprise business operation data, associated enterprise data, judicial data, industrial and commercial data, tax data, negative data and network public opinion; the behavior rating model parameters comprise stock/new data, abnormal transaction data, abnormal account data and other abnormal behavior data.
Preferably, the method further comprises a step of visually displaying the risk account and the account relationship model, wherein the account relationship model is established based on the risk account and the transaction data.
Preferably, the account relationship model comprises a PageRank algorithm, the target account is set as an account number 0, the account directly related to the target account is a layer 1 related account, the target account is set as an account number 1, an account number 2,. and an account number n according to the degree of association, the account number 0 is related to a layer 2 related account through the layer 1 related account, the account number is set as an account number i1, an account number i 2.. and an account number im, i is set to be 1 to n, and the PR value of the account number 0 is calculated by the PageRank algorithm, so that an account related network is constructed.
Preferably, the method further comprises a data reporting and processing process, specifically: reporting, processing and perfecting the risk account and the goodness-of-fit result, wherein the reporting, processing and perfecting process comprises the steps of automatically generating a suspicious report, and manually performing additional recording on the suspicious report, including transaction additional recording, main body additional recording and format verification;
and auditing the completed data, and reporting the generated message to a Chinese anti-money laundering monitoring and analyzing center after the audit is passed.
On the other hand, the invention provides an artificial intelligence anti-money laundering system, which specifically comprises: the system comprises a data acquisition module, a data classification module, a risk scoring module and a risk determination module;
the data acquisition module is used for monitoring the online transaction, acquiring account and transaction data and associating the account and the transaction data to obtain associated data;
the data classification module is used for classifying the account types into a personal account and a legal account and classifying the transactions to obtain different transaction types;
the risk scoring module is used for importing the associated data into a risk scoring model for risk scoring, and if the score is higher than a preset risk threshold value, the associated data is an initial risk account;
the risk determination module is used for inputting transaction data of an initial risk account into an anti-money laundering decision center to calculate the goodness of fit with all money laundering models based on transaction types and account types, finding out the money laundering model with the best goodness of fit, and if the maximum goodness of fit is higher than a preset threshold value, determining the initial risk account as a risk account, wherein the anti-money laundering decision center comprises at least two money laundering models.
Preferably, the risk scoring module is configured to:
acquiring anti-money laundering business data and anti-money laundering derivative data, wherein the anti-money laundering business data and the anti-money laundering derivative data belong to associated data;
inputting the two types of data into a risk rating model for risk rating calculation to obtain a risk rating result;
and associating the risk rating result with a rating object, adding the risk rating result into a rating object list, setting a risk threshold value based on the rating object list, performing initial evaluation on the risk rating result according to a rating model based on the risk threshold value to obtain an initial risk account, wherein the rating result list is updated according to the risk rating result.
Preferably, the system further comprises a visualization module for visually displaying the account relationship, the multi-dimensional business situation and the money laundering risk.
According to the artificial intelligent anti-money laundering method and the artificial intelligent anti-money laundering system, the online transaction process can be monitored in the whole process, the transaction with higher risk is deleted through the risk scoring module, the money laundering model fitting is carried out on the transaction with higher risk, the risk discrimination is carried out for two times, and the accuracy of the risk discrimination is improved; finally, the fitting result is checked and data is reported, and the scheme utilizes the artificial intelligence technology to ensure that the money laundering transaction has accurate recognition degree and high efficiency; an account relation model is established, so that a group partner plan can be identified, and the probability of identifying money laundering plans is improved; and finally, the account relation, the multi-dimensional business situation and the money laundering risk are visually displayed, so that transaction abnormity can be visually observed, and money laundering transaction is assisted to be distinguished.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments are 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 without creative efforts.
FIG. 1 is a schematic diagram of an embodiment of an artificial intelligence anti-money laundering process;
FIG. 2 is a schematic diagram illustrating a risk scoring process in the risk scoring module for accounts and transactions in accordance with an exemplary embodiment;
FIG. 3 is a diagram illustrating a risk rating calculation process in rating indicator management in one embodiment;
FIG. 4 is a flow chart illustrating a data reporting process according to an embodiment;
FIG. 5 is a block diagram of an embodiment of an artificial intelligence anti-money laundering system;
FIG. 6 is a block diagram of an embodiment of an artificial intelligence anti-money laundering system.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. 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 invention.
In the description herein, references to the description of "an embodiment," "a particular embodiment," "an embodiment," "for example," mean that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. The sequence of steps involved in the embodiments is for illustrative purposes to illustrate the implementation of the present application, and the sequence of steps is not limited and can be adjusted as needed.
Fig. 1 is a schematic diagram of an artificial intelligence anti-money laundering process in a specific embodiment, which mainly comprises the following steps:
s1: monitoring the accessed transaction, and acquiring and correlating an account and transaction data;
s2: the method comprises the following steps of dividing account types into individual accounts and legal accounts, and classifying transactions according to transaction types;
s3: importing the account and transaction data into a risk scoring module for risk scoring, and establishing a risk insight scoring system for an admission link and a transaction link, as shown in fig. 2, specifically comprising:
the method comprises the steps of obtaining anti-money laundering business data from a business layer, obtaining anti-money laundering derived data from an anti-money laundering monitoring module, transmitting the two types of data into rating index management for risk rating calculation, associating a calculation result with a rating object and adding the calculation result into a rating object list, carrying out primary evaluation on the calculation result, entering re-evaluation after the primary evaluation is passed, returning back the primary evaluation again after the re-evaluation is not passed, filing the rating result after the re-evaluation is passed, namely adding the rating result into a historical rating result list, and feeding the rating result back to the anti-money laundering monitoring module to optimize a rating model.
As shown in fig. 3, the risk rating calculation in rating indicator management includes: the rating indexes comprise basic indexes, attribute indexes, correlation indexes, transaction characteristics, risk characteristics and early warning characteristics, incoming data are subjected to index classification according to index classification rules in rating index management, the indexes are combined pairwise to form risk sub-items, the risk sub-items are calculated according to a weight rule I to obtain risk factors, the risk factors are calculated according to a weight rule II to obtain risk rating scores, and finally the risk rating scores are converted into risk levels according to a conversion matrix.
The initial evaluation process comprises client identity identification, KYC audit, due diligence investigation and risk level adjustment.
The rating model comprises an admission rating model and a behavior rating model, and the parameters of the admission rating model comprise business operation data, associated enterprise data, judicial data, industrial and commercial data, tax data, negative data and network public opinion; the behavior rating model parameters comprise stock/new data, abnormal transaction data, abnormal account data and other abnormal behavior data.
S4: the account with higher risk level and the transaction are imported into an anti-money laundering decision center for analysis and calculation, and an account relation model is established;
the account relation model comprises a PageRank algorithm, a target account is set as a 0 account, an account directly related to the target account is a layer 1 related account, the target account is sequentially set as an account 1, an account 2, an account n and a layer 2 related account related to the 0 account through the layer 1 related account, the target account is set as an account i1, an account i2, an account im, the value of i is 1 to n, and the PR value of the account 0 is calculated by the PageRank algorithm, so that an account related network is constructed.
S5: for the account with higher risk level, substituting the transaction data into the money laundering model according to the transaction type and the account type to calculate the goodness of fit, and finding the model with the best goodness of fit;
the money laundering model comprises: a model is a money laundering type reflecting a money laundering scenario, and the model comprises a plurality of rules downward, each rule corresponding to a money laundering feature, and the plurality of features reflecting a money laundering scenario.
S6: checking and data reporting are carried out on the account with higher risk level, the transaction and the goodness-of-fit result;
as shown in fig. 4, the data reporting process includes automatically generating a suspicious report, manually performing additional entry on the suspicious report, including transaction additional entry, subject additional entry, and format verification, auditing the completed data, and reporting the generated message to the monitoring and analysis center for money laundering prevention in china after the audit is passed.
S7: and visually displaying the account relation, the multi-dimensional business situation and the money laundering risk.
In another embodiment, an anti-money laundering administrative roster library may also be included: countries, regions or persons for sanctioning measures by other international organizations of the united nations or related countries, other countries, regions or persons determined to be at high risk by local regulatory agencies of the various levels of organizations or by the various levels of organizations based on business experience, countries or regions determined to be NCCT by the FATF, countries or regions determined to lack sufficient law and regulation for money laundering by other international organizations, countries and persons determined to be drug-selling, terrorist or related to other crimes by the international organizations or related countries, offshore financial centers at high risk for money laundering, lists released by the government, united nations, international criminal police organizations.
In another embodiment, as shown in fig. 5, the artificial intelligence anti-money laundering system comprises a decision center, a risk scoring module, a monitoring module, a visualization module, and a database;
the decision center comprises an account relation model and a money laundering model and is used for analyzing and calculating accounts and transactions with higher risk levels and establishing an account relation model; substituting the transaction data into the money laundering model according to the transaction type and the account type to calculate the goodness of fit, and finding a model with the best goodness of fit; checking and data reporting are carried out on the account with higher risk level, the transaction and the goodness-of-fit result;
the risk scoring module is used for carrying out risk scoring on the account and the transaction data and establishing a risk insight scoring system of an admission link and a transaction link, and the process comprises the following steps: the method comprises the steps of obtaining anti-money laundering business data from a business layer, obtaining anti-money laundering derived data from an anti-money laundering monitoring module, transmitting the two types of data into rating index management for risk rating calculation, associating a calculation result with a rating object and adding the calculation result into a rating object list, carrying out primary evaluation on the calculation result, entering re-evaluation after the primary evaluation is passed, returning back the primary evaluation again after the re-evaluation is not passed, filing the rating result after the re-evaluation is passed, namely adding the rating result into a historical rating result list, and feeding the rating result back to the anti-money laundering monitoring module to optimize a rating model.
The monitoring module is used for monitoring the accessed transaction, acquiring and correlating the account and the transaction data; the method comprises the following steps of dividing account types into individual accounts and legal accounts, and classifying transactions according to transaction types;
the database stores a knowledge map, a list base, an important feature list and a feature width list;
the visualization module is used for visually displaying the account relation, the multi-dimensional business situation and the money laundering risk.
In another embodiment, as shown in FIG. 6, an artificial intelligence anti-money laundering system comprises a data acquisition module, a data classification module, a risk scoring module, and a risk determination module;
the data acquisition module is used for monitoring the online transaction, acquiring account and transaction data and associating the account and the transaction data to obtain associated data;
the data classification module is used for classifying the account types into a personal account and a legal account and classifying the transactions to obtain different transaction types;
the risk scoring module is used for importing the associated data into a risk scoring model for risk scoring, and if the score is higher than a preset risk threshold value, the associated data is an initial risk account;
the risk determination module is used for inputting transaction data of an initial risk account into an anti-money laundering decision center to calculate the goodness of fit with all money laundering models based on transaction types and account types, finding out the money laundering model with the best goodness of fit, and if the maximum goodness of fit is higher than a preset threshold value, determining the initial risk account as a risk account, wherein the anti-money laundering decision center comprises at least two money laundering models.
In another particular embodiment, the risk scoring module is configured to:
acquiring anti-money laundering business data and anti-money laundering derivative data, wherein the anti-money laundering business data and the anti-money laundering derivative data belong to associated data;
inputting the two types of data into a risk rating model for risk rating calculation to obtain a risk rating result;
and associating the risk rating result with a rating object, adding the risk rating result into a rating object list, setting a risk threshold value based on the rating object list, performing initial evaluation on the risk rating result according to a rating model based on the risk threshold value to obtain an initial risk account, wherein the rating result list is updated according to the risk rating result.
Other embodiments of the present disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This specification is intended to cover any variations, uses, or adaptations of the specification following, in general, the principles of the specification and including such departures from the present disclosure as come within known or customary practice within the art to which the specification pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the specification being indicated by the following claims.
It will be understood that the present description is not limited to the precise arrangements described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present description is limited only by the appended claims.
Claims (10)
1. An artificial intelligence anti-money laundering method is characterized by comprising the following steps:
monitoring the accessed transaction, acquiring account and transaction data and associating the account and the transaction data to obtain associated data;
the method comprises the following steps of dividing account types into a personal account and a legal account, and classifying transactions to obtain different transaction types;
importing the associated data into a risk scoring model for risk scoring, and if the score is higher than a preset risk threshold value, determining the associated data as an initial risk account;
based on the transaction type and the account type, transaction data of an initial risk account is input into an anti-money laundering decision center to calculate goodness of fit with all money laundering models, a money laundering model with the best goodness of fit is found out, if the maximum goodness of fit is higher than a preset threshold value, the initial risk account is a risk account, wherein the anti-money laundering decision center comprises at least two money laundering models.
2. The artificial intelligence money laundering method according to claim 1, wherein the step of importing the associated data into a risk scoring model for risk scoring, and if the score is higher than a preset risk threshold, the score is an initial risk account, comprises the steps of:
acquiring anti-money laundering business data and anti-money laundering derivative data, wherein the anti-money laundering business data and the anti-money laundering derivative data belong to associated data;
inputting the two types of data into a risk rating model for risk rating calculation to obtain a risk rating result;
and associating the risk rating result with a rating object, adding the risk rating result into a rating object list, setting a risk threshold value based on the rating object list, performing initial evaluation on the risk rating result according to a rating model based on the risk threshold value to obtain an initial risk account, wherein the rating result list is updated according to the risk rating result, and the rating model is optimized according to the rating result.
3. The artificial intelligence anti-money laundering method according to claim 2, wherein the risk rating calculation comprises an index calculation and a feature calculation;
the indexes comprise basic indexes, attribute indexes and associated indexes; the characteristics comprise transaction characteristics, risk characteristics and early warning characteristics;
the index calculation and the feature calculation specifically include the following processes:
performing index classification on the anti-money laundering business data and the anti-money laundering derivative data according to an index classification rule in the rating index management to obtain a classification result;
combining the classification results into risk sub-items pairwise, and calculating the risk sub-items according to a first weight rule to obtain risk factors, wherein the first weight rule is a weight ratio rule preset according to the influence degree of the index classification results;
calculating the risk factors according to a second weight rule to obtain a risk rating score, wherein the second weight rule is a weight ratio rule preset according to the influence degree of the risk factors;
and converting the risk rating score into a risk grade according to the grading grade conversion matrix.
4. The artificial intelligence anti-money laundering method according to claim 2, wherein the preliminary evaluation operations include customer identification, KYC audit, due diligence and risk level adjustment.
5. The artificial intelligence anti-money laundering method according to claim 2, wherein the rating model comprises an admission rating model and a behavior rating model, and the admission rating model parameters comprise business data, associated enterprise data, judicial data, industrial and commercial data, tax data, negative data, network public opinion; the behavior rating model parameters comprise stock/new data, abnormal transaction data, abnormal account data and other abnormal behavior data.
6. The artificial intelligence anti-money laundering method according to claim 1, further comprising a step of visually displaying a risk account and an account relationship model, wherein the account relationship model is established based on the risk account and transaction data.
7. The artificial intelligence money laundering method according to claim 6, wherein the account relationship model comprises a PageRank algorithm, the target account is set as a 0 account, the account directly associated with the target account is a layer 1 associated account, the account is set as an account 1, an account 2, an.
8. The artificial intelligence anti-money laundering method according to claim 1, further comprising a data reporting and processing process, specifically: reporting, processing and perfecting the risk account and the goodness-of-fit result, wherein the reporting, processing and perfecting process comprises the steps of automatically generating a suspicious report, and manually performing additional recording on the suspicious report, including transaction additional recording, main body additional recording and format verification;
and auditing the completed data, and reporting the generated message to a Chinese anti-money laundering monitoring and analyzing center after the audit is passed.
9. An artificial intelligence money laundering system is characterized by comprising a data acquisition module, a data classification module, a risk scoring module and a risk determination module;
the data acquisition module is used for monitoring the online transaction, acquiring account and transaction data and associating the account and the transaction data to obtain associated data;
the data classification module is used for classifying the account types into a personal account and a legal account and classifying the transactions to obtain different transaction types;
the risk scoring module is used for importing the associated data into a risk scoring model for risk scoring, and if the score is higher than a preset risk threshold value, the associated data is an initial risk account;
the risk determination module is used for inputting transaction data of an initial risk account into an anti-money laundering decision center to calculate the goodness of fit with all money laundering models based on transaction types and account types, finding out the money laundering model with the best goodness of fit, and if the maximum goodness of fit is higher than a preset threshold value, determining the initial risk account as a risk account, wherein the anti-money laundering decision center comprises at least two money laundering models.
10. The artificial intelligence anti-money laundering system according to claim 9, wherein the risk scoring module is configured to: acquiring anti-money laundering business data and anti-money laundering derivative data, wherein the anti-money laundering business data and the anti-money laundering derivative data belong to associated data;
inputting the two types of data into a risk rating model for risk rating calculation to obtain a risk rating result;
and associating the risk rating result with a rating object, adding the risk rating result into a rating object list, setting a risk threshold value based on the rating object list, performing initial evaluation on the risk rating result according to a rating model based on the risk threshold value to obtain an initial risk account, wherein the rating result list is updated according to the risk rating result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110580253.0A CN113256121A (en) | 2021-05-26 | 2021-05-26 | Artificial intelligent money laundering method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110580253.0A CN113256121A (en) | 2021-05-26 | 2021-05-26 | Artificial intelligent money laundering method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113256121A true CN113256121A (en) | 2021-08-13 |
Family
ID=77184682
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110580253.0A Pending CN113256121A (en) | 2021-05-26 | 2021-05-26 | Artificial intelligent money laundering method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113256121A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114742655A (en) * | 2022-06-13 | 2022-07-12 | 杭银消费金融股份有限公司 | Anti-money laundering behavior recognition system based on machine learning |
| CN116596539A (en) * | 2023-04-18 | 2023-08-15 | 北京邮电大学 | Money backwashing method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109767322A (en) * | 2018-12-20 | 2019-05-17 | 平安科技（深圳）有限公司 | Suspicious transaction analysis method, apparatus and computer equipment based on big data |
| CN109767326A (en) * | 2018-12-20 | 2019-05-17 | 平安科技（深圳）有限公司 | Suspicious transaction reporting generation method, device, computer equipment and storage medium |
| CN109767327A (en) * | 2018-12-20 | 2019-05-17 | 平安科技（深圳）有限公司 | Customer information acquisition and its application method based on anti money washing |
| CN109949154A (en) * | 2018-12-17 | 2019-06-28 | 深圳平安综合金融服务有限公司 | Customer information classification method, device, computer equipment and storage medium |
| CN110264326A (en) * | 2019-05-24 | 2019-09-20 | 阿里巴巴集团控股有限公司 | Identify the method, device and equipment of abnormal account aggregation and adventure account set |
-
2021
- 2021-05-26 CN CN202110580253.0A patent/CN113256121A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109949154A (en) * | 2018-12-17 | 2019-06-28 | 深圳平安综合金融服务有限公司 | Customer information classification method, device, computer equipment and storage medium |
| CN109767322A (en) * | 2018-12-20 | 2019-05-17 | 平安科技（深圳）有限公司 | Suspicious transaction analysis method, apparatus and computer equipment based on big data |
| CN109767326A (en) * | 2018-12-20 | 2019-05-17 | 平安科技（深圳）有限公司 | Suspicious transaction reporting generation method, device, computer equipment and storage medium |
| CN109767327A (en) * | 2018-12-20 | 2019-05-17 | 平安科技（深圳）有限公司 | Customer information acquisition and its application method based on anti money washing |
| CN110264326A (en) * | 2019-05-24 | 2019-09-20 | 阿里巴巴集团控股有限公司 | Identify the method, device and equipment of abnormal account aggregation and adventure account set |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114742655A (en) * | 2022-06-13 | 2022-07-12 | 杭银消费金融股份有限公司 | Anti-money laundering behavior recognition system based on machine learning |
| CN114742655B (en) * | 2022-06-13 | 2022-09-02 | 杭银消费金融股份有限公司 | Anti-money laundering behavior recognition system based on machine learning |
| CN116596539A (en) * | 2023-04-18 | 2023-08-15 | 北京邮电大学 | Money backwashing method and system |
| CN116596539B (en) * | 2023-04-18 | 2024-02-09 | 北京邮电大学 | Money backwashing method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Segovia-Vargas | Money laundering and terrorism financing detection using neural networks and an abnormality indicator | |
| González et al. | Characterization and detection of taxpayers with false invoices using data mining techniques | |
| Wang | A comprehensive survey of data mining-based accounting-fraud detection research | |
| JP6162242B2 (en) | Transaction monitoring system | |
| US7427016B2 (en) | System and method for screening for fraud in commercial transactions | |
| US20170262852A1 (en) | Database monitoring system | |
| Li et al. | Identifying the signs of fraudulent accounts using data mining techniques | |
| EP2461280A1 (en) | Method and system for dynamically detecting illegal activity | |
| CN109472610A (en) | A kind of bank transaction is counter to cheat method and system, equipment and storage medium | |
| CN113994323A (en) | Intelligent alarm system | |
| CN113256121A (en) | Artificial intelligent money laundering method and system | |
| Akinbowale et al. | The integration of forensic accounting and big data technology frameworks for internal fraud mitigation in the banking industry | |
| Rouhollahi | Towards artificial intelligence enabled financial crime detection | |
| Mahootiha et al. | Designing a new method for detecting money laundering based on social network analysis | |
| Dawe | Conducting national money laundering or financing of terrorism risk assessment | |
| CN115879548B (en) | Knowledge graph construction method and system for customer identity recognition | |
| Лєонов et al. | Forecasting the risk of money laundering through financial intermediaries | |
| Palshikar et al. | Financial security against money laundering: A survey | |
| CN114140245A (en) | Organization risk assessment method, device and equipment and computer storage medium | |
| Şen et al. | Detecting falsified financial statements using data mining: empirical research on finance sector in Turkey | |
| Kamau | An investigation into the causes and characteristics of fraud in Kenyan SACCOs and whether Benford's Law can be used to detect fraud in the accounting data | |
| Danenas | Intelligent financial fraud detection and analysis: a survey of recent patents | |
| Rose | Modernizing check fraud detection with machine learning | |
| Khanuja et al. | Monitor and detect suspicious transactions with database forensics and Dempster-Shafer theory of evidence | |
| Nwafor et al. | The use of business intelligence and predictive analytics in detecting and managing occupational fraud in Nigerian banks |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210813 |
|
| RJ01 | Rejection of invention patent application after publication |