CN114399384A - Risk strategy generation method, system and device based on privacy calculation - Google Patents
Risk strategy generation method, system and device based on privacy calculation Download PDFInfo
- Publication number
- CN114399384A CN114399384A CN202210299398.8A CN202210299398A CN114399384A CN 114399384 A CN114399384 A CN 114399384A CN 202210299398 A CN202210299398 A CN 202210299398A CN 114399384 A CN114399384 A CN 114399384A
- Authority
- CN
- China
- Prior art keywords
- data
- risk
- reconstructed
- strategy
- module
- 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
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a risk strategy generation method, a system and a device based on privacy computation, belonging to the technical field of risk identification, comprising the steps that a data provider acquires original data required by a target service, and reconstructs the original data to acquire reconstructed data and sends the reconstructed data to a data user; a data user acquires a data label of a target service, and calculates an information value index value of each characteristic of reconstruction data by combining the acquired reconstruction data; screening effective characteristics from the reconstructed data according to the calculated information value index value; according to the obtained data labels and the screened effective characteristics, performing box separation processing on the reconstructed data, and calculating risk indexes of each box separation; the risk strategy for solving the target service problem is generated by using the screened effective characteristics and the calculated risk indexes, and the risk strategy is deployed to the online service.
Description
Technical Field
The invention belongs to the technical field of risk identification, and particularly relates to a risk strategy generation method, system and device based on privacy computation.
Background
With the rapid development of internet technology, online businesses in the financial field, such as credit loans and mortgage loans, also leap forward suddenly, but the businesses also bring certain risks while developing rapidly, including economic losses caused by overdue default of customers and economic losses caused by fraud of lawless persons by various means, so how to improve the risk identification capability of the online loan businesses becomes a key problem for financial enterprises to improve the income.
In order to identify risks in online business, financial enterprises often need to access a large amount of external data to support risk policy generation, but under the requirements of relevant laws and regulations, enterprises need to strictly protect personal privacy data and comply with data security requirements.
At present, the traditional privacy calculation provides privacy protection by randomizing data, and generates a policy by using randomly disturbed data, however, the method has inevitable problems, on one hand, the policy effect of the randomized data generation is general, on the other hand, the method is easy to attack, and the privacy security of the data is difficult to guarantee.
Therefore, for financial enterprises, it is an urgent technical problem to ensure the data privacy security of customers and to generate business risk policies efficiently and accurately.
Disclosure of Invention
The invention provides a risk strategy generation method, a system and a device based on privacy calculation, aiming at the problems that the existing generated risk strategy has a general effect, needs a large amount of client data in order to improve the accuracy of the risk strategy and cannot protect the privacy of the client data.
In order to solve the above problems, the present invention adopts the following technical solutions.
A risk strategy generation method based on privacy computation adopts the following steps:
step 1: the data provider acquires original data required by a target service, reconstructs the original data to acquire reconstructed data, and sends the reconstructed data to the data user;
step 2: a data user acquires a data label of a target service, and calculates an information value index value of each characteristic of reconstruction data by combining the reconstruction data acquired in the step 1;
and step 3: the data user selects effective characteristics from the reconstructed data according to the information value index value calculated in the step 2;
and 4, step 4: the data user carries out box separation processing on the reconstructed data according to the data labels obtained in the step 2 and the effective characteristics screened in the step 3, and calculates risk indexes corresponding to all boxes;
and 5: the data user uses the effective characteristics screened in the step 3 and the risk indexes calculated in the step 4 to generate a risk strategy for solving the target business problem;
step 6: and the data user deploys the risk strategy to the online business.
For the purpose of protecting the privacy of the client, it is preferable that the original data reconstructed in step 1 is reconstructed by using an auto-encoder.
In order to make the original data and the reconstructed data have common statistical characteristics and have differences, further, the self-encoder firstly uses the encoder to perform dimension reduction compression on the data, and then uses the decoder to perform dimension increase decompression on the data, so as to achieve the effect of data reconstruction,
in order to make the data more accurate, the data tag in step 2 is preferably used for judging whether the client has a risk according to the history of the client data, so as to mark the data as different samples.
In order to reduce the influence of the feature redundancy on the result, preferably, the effective feature screened in step 3 is a preset index threshold, the information value index value calculated by each feature is compared with the index threshold, the effective feature is greater than the index threshold, and the ineffective feature is less than or equal to the index threshold.
In order to obtain a more accurate calculated data result, it is preferable that the binning processing is performed on the reconstructed data in step 4 by using an equal frequency binning method.
In order to make the accuracy of the risk policy higher, the risk policy generated in step 5 is preferably a policy set of each valid feature.
In order to protect the privacy of the client of the target data, preferably, the risk policy is used in the online service by encoding and reconstructing the target data by the data provider, and the data consumer uses the risk policy to distinguish the encoded and reconstructed target data.
A privacy computation-based risk policy generation system, comprising:
the data reconstruction module is used for acquiring data and reconstructing the data;
the index calculation module is used for acquiring a data label of the target service, calculating the reconstructed data by using the data label and acquiring information value index values of all the characteristics;
the characteristic screening module is used for screening effective characteristics according to the information value index values of all the characteristics;
the box separating module is used for carrying out box separating processing on the reconstructed data;
the risk calculation module is used for calculating the grouped reconstructed data according to the data label of the target service and the effective characteristics obtained by the characteristic screening module to obtain risk indexes corresponding to the bins;
the strategy generating module is used for generating a risk strategy for solving the target business problem by combining the effective characteristics obtained by the characteristic screening module and the risk indexes calculated by the risk calculating module;
and the business judging module is used for judging the target data reconstructed by the data reconstruction module according to the risk strategy generated by the strategy generating module.
A risk policy generation apparatus based on privacy computation, the apparatus comprising a service processor and a distributed memory, the service processor being connected to the memory, the distributed memory having stored therein a self-service manager configured to store machine-readable instructions, the service processor executing the self-service manager, the instructions when executed by the processor, to implement a risk policy generation method based on privacy computation as described above.
A risk strategy generation method, a system and a device based on privacy calculation enable a data provider to reconstruct original data, effective data can still be provided on the premise of protecting privacy of a client, a data user acquires a data label of a target service first, calculates information value index values of all characteristics, screens out effective characteristics from reconstructed data, calculates risk indexes corresponding to all boxes and generates a risk strategy for solving the problem of the target service, and therefore the problem that security of the client privacy is difficult to guarantee by external data can be solved, and accuracy of the risk strategy can be improved.
Compared with the prior art, the invention has the beneficial effects that:
(1) according to the invention, the external data is reconstructed through the self-encoder, the self-encoder comprises an encoder and a decoder, the encoder and the decoder can be multi-layer perceptrons, so that on one hand, the original data and the reconstructed data have common statistical characteristics, the consistency of the effect of generating strategies based on the original data and the reconstructed data can be ensured, on the other hand, the specific data of the original data and the reconstructed data are different, and the privacy of a client can be protected by using the reconstructed data generation strategy;
(2) according to the method, the risk distribution of each characteristic calculated by the data label of the target service is correlated, the information value index value of each characteristic is calculated, effective characteristics are screened out, and the risk strategy for the target service is finally generated, so that the accuracy of the risk strategy can be more accurate, and the risk occurrence rate is reduced;
(3) according to the method, the reconstructed data is subjected to binning processing, so that the deviation of a calculation result can be reduced, feature derivation is facilitated, feature dimensions are improved, and a risk index result corresponding to each bin is more accurate.
Drawings
In order to more clearly illustrate the embodiments or exemplary technical solutions of the present application, the drawings needed to be used in the embodiments or exemplary descriptions 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 therefore should not be considered as limiting the scope, and it is also possible for those skilled in the art to obtain other drawings according to the drawings without inventive efforts.
FIG. 1 is a schematic representation of the steps of the present invention;
FIG. 2 is a schematic flow chart of the present invention;
FIG. 3 is a schematic diagram of data reconstruction according to the present invention;
FIG. 4 is a schematic diagram of the system of the present invention;
FIG. 5 is a schematic diagram of the apparatus of the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application, it is obvious that the described embodiments are a part of the embodiments of the present application, but not all of the embodiments, and generally, components of the embodiments of the present application described and illustrated in the drawings herein can be arranged and designed in various different configurations.
Therefore, the following detailed description of the embodiments of the present application, as presented in the figures, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application, and all other embodiments that can be derived by one of ordinary skill in the art based on the embodiments in the present application without making creative efforts fall within the scope of the claimed application.
Example 1
As shown in fig. 1 and fig. 2, a risk policy generation method based on privacy computation includes the following specific processes:
determining original data and a data provider required by a target service, wherein the target service can be loan service, guarantee service and other services, the data provider refers to a company capable of providing original data service and comprises data such as multi-head loan, payment behavior, credit history and the like of a client, the data provider acquires the original data required by the target service, the data provider reconstructs the original data, the reconstruction of the original data is performed by adopting a self-encoder, the self-encoder is a specific form of a neural network, the self-encoder performs dimension reduction compression on the data by using an encoder, and then performs dimension increase decompression on the data by using a decoder, so that the effect of data reconstruction is achieved, and the reconstructed data is sent to a data user after the reconstructed data is obtained.
As shown in fig. 3, the encoder and the decoder may be implemented as a multi-layer perceptron, in which the number of neurons in each layer decreases layer by layer, that is, the data dimension changes from 8 to 4 to 2, so as to compress the input X layer by layer, and in which the number of neurons in each layer increases layer by layer, that is, the data dimension changes from 2 to 4 to 8, so as to recover the data and obtain the reconstructed data.
The data using party judges whether the client has risks according to the historical records of the client data, if the client of the target service is a risk client, the data label of the client can be marked as a black sample, if the client of the target service is a non-risk client, the data label of the client can be marked as a white sample, the data is marked as different samples, the data label of the target service is obtained, and the information value index value of each characteristic of the reconstruction data is calculated by combining the obtained reconstruction data.
The data user presets an index threshold, compares the information value index value calculated by each feature with the index threshold, the information value index value which is greater than the index threshold is effective feature, the information value index which is less than or equal to the index threshold is ineffective feature, the feature can be understood as fields of 'loan amount', 'loan times', 'payment times', and the like, and the effective feature can be fields of 'loan amount', and the like, wherein the information value index value is higher.
And the data user performs box separation processing on the reconstructed data by adopting an equal frequency box separation method according to the obtained data labels and the screened effective characteristics, and calculates the risk indexes corresponding to the boxes.
And the data user uses the screened effective characteristics and the calculated risk indexes to generate a risk strategy for solving the target business problem, wherein the risk strategy is a strategy set of each effective characteristic.
And the data user deploys the risk strategy to the online service, the data provider encodes and reconstructs the target data, and the data user discriminates the encoded and reconstructed target data by using the risk strategy.
According to the description, in the embodiment, the original data are reconstructed by the data provider, effective data can be still provided on the premise of protecting the privacy of the client, the data user firstly obtains the data label of the target service, then calculates the information value index value of each characteristic, then screens out the effective characteristic from the reconstructed data, then calculates the risk index corresponding to each sub-box and generates the risk strategy for solving the problem of the target service, the problem that the external data are difficult to ensure the privacy safety of the client can be solved, and the accuracy of the risk strategy can be improved.
Example 2
As shown in fig. 4, a risk policy generation system based on privacy computation includes:
the data reconstruction module is used for acquiring data and reconstructing the data;
the index calculation module is used for acquiring a data label of the target service, calculating the reconstructed data by using the data label and acquiring information value index values of all the characteristics;
the characteristic screening module is used for screening effective characteristics according to the information value index values of all the characteristics;
the box separating module is used for carrying out box separating processing on the reconstructed data;
the risk calculation module is used for calculating the grouped reconstructed data according to the data label of the target service and the effective characteristics obtained by the characteristic screening module to obtain risk indexes corresponding to the bins;
the strategy generating module is used for generating a risk strategy for solving the target business problem by combining the effective characteristics obtained by the characteristic screening module and the risk indexes calculated by the risk calculating module;
and the business judging module is used for judging the target data reconstructed by the data reconstruction module according to the risk strategy generated by the strategy generating module.
According to the description, in the embodiment, the original data is reconstructed through the data reconstruction module, the index calculation module calculates information value index values of all the characteristics, the characteristic screening module screens out effective characteristics, the box separation module performs box separation processing on the reconstructed data, the risk calculation module calculates risk indexes of all the boxes, the strategy generation module generates a risk strategy for solving a target business problem, and the business judgment module judges the target data reconstructed by the data reconstruction module, so that the accuracy of the risk strategy can be more accurate while the privacy of client data is protected.
Example 3
As shown in fig. 5, a risk policy generation apparatus based on privacy computation includes a service processor and a distributed memory, the service processor is connected to the memory, the distributed memory stores a service self-management program configured to store machine-readable instructions, the service processor executes the service self-management program, and the instructions when executed by the processor implement the risk policy generation method based on privacy computation according to embodiment 1.
According to the description, in the embodiment, the original data are reconstructed by the data provider, effective data can be still provided on the premise of protecting the privacy of the client, the data user firstly obtains the data label of the target service, then calculates the information value index value of each characteristic, then screens out the effective characteristic from the reconstructed data, then calculates the risk index corresponding to each sub-box and generates the risk strategy for solving the problem of the target service, the problem that the external data are difficult to ensure the privacy safety of the client can be solved, and the accuracy of the risk strategy can be improved.
The above examples are merely representative of preferred embodiments of the present invention, and the description thereof is more specific and detailed, but not to be construed as limiting the scope of the present invention. It should be noted that, for those skilled in the art, various changes, modifications and substitutions can be made without departing from the spirit of the present invention, and these are all within the scope of the present invention.
Claims (10)
1. A risk strategy generation method based on privacy computation is characterized by comprising the following steps:
step 1: the data provider acquires original data required by a target service, reconstructs the original data to acquire reconstructed data, and sends the reconstructed data to the data user;
step 2: a data user acquires a data label of a target service, and calculates an information value index value of each characteristic of reconstruction data by combining the reconstruction data acquired in the step 1;
and step 3: the data user screens effective characteristics from the reconstructed data according to the information value index value calculated in the step 2;
and 4, step 4: the data user carries out box separation processing on the reconstructed data according to the data labels obtained in the step 2 and the effective characteristics screened in the step 3, and calculates risk indexes corresponding to all boxes;
and 5: the data user uses the effective characteristics screened in the step 3 and the risk indexes calculated in the step 4 to generate a risk strategy for solving the target business problem;
step 6: and the data user deploys the risk strategy to the online business.
2. The method of claim 1, wherein the risk policy generation method based on privacy computation is characterized in that: the original data is reconstructed in step 1 by using a self-encoder.
3. The method of claim 2, wherein the risk policy generation method based on privacy computation is characterized in that: the self-encoder firstly uses the encoder to perform dimensionality reduction compression on data, and then uses the decoder to perform dimensionality increase decompression on the data, so as to achieve the effect of data reconstruction.
4. The method of claim 1, wherein the risk policy generation method based on privacy computation is characterized in that: the data label in step 2 is to judge whether the client has risks according to the history of the client data, so as to mark the data as different samples.
5. The method of claim 1, wherein the risk policy generation method based on privacy computation is characterized in that: the effective features screened in the step 3 are preset index threshold values, the information value index values calculated by the features are compared with the index threshold values, the effective features are more than the index threshold values, and the invalid features are less than or equal to the index threshold values.
6. The method of claim 1, wherein the risk policy generation method based on privacy computation is characterized in that: and 4, performing box separation on the reconstructed data by adopting an equal frequency box separation method.
7. The method of claim 1, wherein the risk policy generation method based on privacy computation is characterized in that: the risk policy generated in step 5 is a policy set of each effective feature.
8. The method of claim 1, wherein the risk policy generation method based on privacy computation is characterized in that: the method for using the risk strategy on-line service is that a data provider encodes and reconstructs target data, and a data user uses the risk strategy to judge the encoded and reconstructed target data.
9. A risk policy generation system based on privacy computation, comprising:
the data reconstruction module is used for acquiring data and reconstructing the data;
the index calculation module is used for acquiring a data label of the target service, calculating the reconstructed data by using the data label and acquiring information value index values of all the characteristics;
the characteristic screening module is used for screening effective characteristics according to the information value index values of all the characteristics;
the box separating module is used for carrying out box separating processing on the reconstructed data;
the risk calculation module is used for calculating the grouped reconstructed data according to the data label of the target service and the effective characteristics obtained by the characteristic screening module to obtain risk indexes corresponding to the bins;
the strategy generating module is used for generating a risk strategy for solving the target business problem by combining the effective characteristics obtained by the characteristic screening module and the risk indexes calculated by the risk calculating module;
and the business judging module is used for judging the target data reconstructed by the data reconstruction module according to the risk strategy generated by the strategy generating module.
10. A risk policy generation apparatus based on privacy computation, the apparatus comprising a service processor and a distributed memory, the service processor being connected to the memory, the distributed memory having a self-managed service program stored therein and configured to store machine-readable instructions, the self-managed service program being executed by the service processor, the instructions when executed by the processor implementing the risk policy generation method based on privacy computation according to claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210299398.8A CN114399384A (en) | 2022-03-25 | 2022-03-25 | Risk strategy generation method, system and device based on privacy calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210299398.8A CN114399384A (en) | 2022-03-25 | 2022-03-25 | Risk strategy generation method, system and device based on privacy calculation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114399384A true CN114399384A (en) | 2022-04-26 |
Family
ID=81234691
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210299398.8A Pending CN114399384A (en) | 2022-03-25 | 2022-03-25 | Risk strategy generation method, system and device based on privacy calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114399384A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117032828A (en) * | 2023-08-14 | 2023-11-10 | 江苏智先生信息科技有限公司 | Batch automatic configuration method for customized special system platform |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110443618A (en) * | 2019-07-10 | 2019-11-12 | 阿里巴巴集团控股有限公司 | The generation method and device of air control strategy |
| CN110472827A (en) * | 2019-07-10 | 2019-11-19 | 阿里巴巴集团控股有限公司 | System strategy method for early warning, device, server and readable storage medium storing program for executing |
| US20200104470A1 (en) * | 2016-06-10 | 2020-04-02 | OneTrust, LLC | Data processing systems and methods for efficiently assessing the risk of privacy campaigns |
| CN113297804A (en) * | 2021-06-24 | 2021-08-24 | 上海交通大学 | Anomaly detection method and system based on U-Transformer multi-level feature reconstruction |
| CN113610107A (en) * | 2021-07-02 | 2021-11-05 | 同盾科技有限公司 | Feature optimization method and device |
| CN114139147A (en) * | 2021-11-30 | 2022-03-04 | 中国工商银行股份有限公司 | Targeted attack defense method and device |
-
2022
- 2022-03-25 CN CN202210299398.8A patent/CN114399384A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200104470A1 (en) * | 2016-06-10 | 2020-04-02 | OneTrust, LLC | Data processing systems and methods for efficiently assessing the risk of privacy campaigns |
| CN110443618A (en) * | 2019-07-10 | 2019-11-12 | 阿里巴巴集团控股有限公司 | The generation method and device of air control strategy |
| CN110472827A (en) * | 2019-07-10 | 2019-11-19 | 阿里巴巴集团控股有限公司 | System strategy method for early warning, device, server and readable storage medium storing program for executing |
| CN113297804A (en) * | 2021-06-24 | 2021-08-24 | 上海交通大学 | Anomaly detection method and system based on U-Transformer multi-level feature reconstruction |
| CN113610107A (en) * | 2021-07-02 | 2021-11-05 | 同盾科技有限公司 | Feature optimization method and device |
| CN114139147A (en) * | 2021-11-30 | 2022-03-04 | 中国工商银行股份有限公司 | Targeted attack defense method and device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117032828A (en) * | 2023-08-14 | 2023-11-10 | 江苏智先生信息科技有限公司 | Batch automatic configuration method for customized special system platform |
| CN117032828B (en) * | 2023-08-14 | 2024-01-26 | 江苏智先生信息科技有限公司 | Batch automatic configuration method for customized special system platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | SEC's cybersecurity disclosure guidance and disclosed cybersecurity risk factors | |
| Smith et al. | Do auditors price breach risk in their audit fees? | |
| Bose et al. | Adoption of identity theft countermeasures and its short-and long-term impact on firm value. | |
| Bose et al. | The impact of adoption of identity theft countermeasures on firm value | |
| US20100057622A1 (en) | Distributed Quantum Encrypted Pattern Generation And Scoring | |
| US20130036038A1 (en) | Financial activity monitoring system | |
| CN114399384A (en) | Risk strategy generation method, system and device based on privacy calculation | |
| US11356469B2 (en) | Method and apparatus for estimating monetary impact of cyber attacks | |
| Abdulla | Digital image steganography: challenges, investigation, and recommendation for the future direction | |
| Serrasqueiro et al. | Risk reporting: do country-level institutional forces really matter? | |
| Cong et al. | Blockchain forensics and crypto-related cybercrimes | |
| Ming et al. | Contagion or flight‐to‐quality? The linkage between oil price and the US dollar based on the local Gaussian approach | |
| CA3104372A1 (en) | System and method for multivariate anomaly detection | |
| Hogan | A Global Comparison of Corporate Value Adjustments to News of Cyber Attacks | |
| Yusoff et al. | Areas of Technology That Helps in Combating Money Laundering: A Concept Paper | |
| Nobanee et al. | A Disclosure Index To Measure The Extent Of Anti-Fraud Reporting In Banks | |
| Leung et al. | Indirect financial loss of phishing to global market | |
| Li et al. | Accountants perception on effectiveness of corporate fraud detection and prevention methods in Ghana | |
| CN111882330A (en) | Financial fraud prevention analysis method, device, equipment and storage medium | |
| Gadirova | The Impacts of Cyberattacks on Private Firms' Cash Holdings | |
| Lee et al. | When does financial misconduct result in external whistle-blowing: A comparison between external whistle-blowing and internal reporting | |
| Basu et al. | The shape of the cybersecurity insurance industry: 2015-2020. | |
| Pavlidis | RegTech and the Fight against Money Laundering: Mapping the Challenges | |
| Liu et al. | Big Data Analysis with No Digital Footprints Available: Evidence from Cyber-Telecom Fraud | |
| CN117952619B (en) | Risk behavior analysis method, system and computer readable medium based on digital RMB wallet account correlation |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20220426 |