CN112200652A - SDK system based on credit investigation message variable processing and customer portrait and processing method thereof - Google Patents
SDK system based on credit investigation message variable processing and customer portrait and processing method thereof Download PDFInfo
- Publication number
- CN112200652A CN112200652A CN202010711327.5A CN202010711327A CN112200652A CN 112200652 A CN112200652 A CN 112200652A CN 202010711327 A CN202010711327 A CN 202010711327A CN 112200652 A CN112200652 A CN 112200652A
- Authority
- CN
- China
- Prior art keywords
- credit
- sdk
- credit investigation
- customer
- variable
- 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.)
- Granted
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/80—Information retrieval; Database structures therefor; File system structures therefor of semi-structured data, e.g. markup language structured data such as SGML, XML or HTML
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Finance (AREA)
- Mathematical Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- General Business, Economics & Management (AREA)
- Algebra (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention relates to the technical field of financial wind control, in particular to an SDK (software development kit) system based on credit investigation message variable processing and customer portrait and a processing method thereof, and relates to a human credit investigation docking system which is used for acquiring human credit investigation messages and respectively acquiring HTML (hypertext markup language) and XML (extensible markup language) formats; the credit investigation variable processing SDK inputs an XML request message of the personal credit investigation at an API interface and outputs a derivative variable containing 200+ credit investigation and a client image code; the data platform is used for docking an external data source interface and transmitting data to the analysis library for data analysis; and the IDE of the decision engine platform realizes the writing of the derived variable function and the rule strategy configuration. The method is used for processing the derivative variables of the pedestrian credit based on the SDK, when the sizes of the XML messages of the pedestrian credit are respectively 20KB,80KB and 1.7M, the result shows that all the calculation results of the derivative variables can be obtained within 100ms, the processing speed is very high, the system performance is more than 5 times faster than that of the derivative variables processed based on the database, the accuracy can be ensured, and the development time is short.
Description
Technical Field
The invention relates to the technical field of financial wind control, in particular to an SDK system based on credit investigation message variable processing and customer portrait and a processing method thereof.
Background
When a general bank or credit financial institution processes a credit or withdrawal application of a borrower, the general bank or credit financial institution generally queries the credit investigation report information of the borrower or other external credit investigation information as an approval basis. And the risk control team processes a plurality of derived variables based on basic original variables in the human behavior credit report or a plurality of original variables into a plurality of derived variables together, and the variables are used as the basis for configuring the risk rule strategy by the wind control decision engine platform.
Currently, many banks or credit financial institutions adopt a mode of uniformly transmitting the data message of the people's bank credit report to a decision engine, process derived variables required by a strategy in the decision engine, and use the variables in a rule strategy of the decision engine. In addition, some financial institutions establish credit investigation data platforms facing the institutions, perform database dropping on queried credit investigation report messages, split the credit investigation report messages into different data tables, process required derived variables in the database, store the processed derived variables in the database by using special tables, and return a derived variable set of a certain applicant in an interface mode when a decision system needs to use the processed derived variables.
If the whole passenger credit investigation report message is transmitted to the decision engine platform to process the wind control variable, when the credit record content of the applicant credit investigation report is more and the data volume is larger, the decision engine has larger data processing overhead and certain influence on performance. Meanwhile, the number of information items in the original credit investigation report is also large, and after all the information is transmitted into the decision engine, it is difficult for risk personnel to select some required variables during policy configuration.
When a mode of processing credit investigation derivative variables by a database is adopted, an original message of a person credit investigation report needs to be dropped into the database, the original message is analyzed and split into the dropped database, when derivative variable calculation is carried out, a variable processing program needs to be called, the processed derivative variables also need to be dropped into the database, and then the derived variables are returned to a decision system in an interface mode.
Disclosure of Invention
Aiming at the defects of the prior art, the invention discloses an SDK system based on credit investigation message variable processing and customer portrait and a processing method thereof, aiming at ensuring that the logic of human credit investigation derivative variable processing can realize unified management and can also well ensure the processing performance and the convenience of use on a risk decision engine system. In addition, because the derived variables of the people's bank credit are the basis of wind control, the same variable sets can be reused in multiple banks or financial institutions, so that the mode of processing the variables and generating the customer image codes is designed into an SDK (software development kit), the reusability can be improved, the expenses brought by multiple projects in the system development process can be reduced, and the online efficiency of the system can be improved.
The invention is realized by the following technical scheme:
in a first aspect, the present invention discloses an SDK system based on credit report variable processing and customer portrait, comprising,
the personnel credit investigation docking system is used for acquiring a personnel credit investigation request message and respectively acquiring HTML (hypertext markup language) and XML (extensible markup language) formats;
the credit investigation SDK inputs an XML request message of the personal credit investigation at an API interface and outputs a derivative variable containing 200+ credit investigation and a client image code;
the data platform is used for docking an external data source and transmitting data to the analysis library for data analysis;
and the IDE of the decision engine platform is used for realizing the writing and rule strategy configuration of the derived variable function.
Furthermore, the module of the credit investigation SDK internally develops a processing function of derived variables based on a decision engine platform and determines the image code of the client based on the strategy by configuring a rule set.
Furthermore, the image codes of the customers represent customers with different customer group classifications or risks, and the generated derivative variables are derivative variables commonly used in daily risk strategies.
Furthermore, the IDE of the decision engine may implement the compiling of the derived variable function and the rule policy configuration, and package them into a software runtime package, which is a compiled program.
Furthermore, the software package is embedded in the credit investigation SDK, and when executed, the software package itself runs in the process of the credit investigation SDK, and all the software package is executed in the memory.
Furthermore, the software packages are all executed in the memory and do not relate to IO operation of the database.
In a second aspect, the present invention discloses a service processing method for an SDK system based on credit investigation message variable processing and client portrait, wherein the processing method uses the SDK system based on credit investigation message variable processing and client portrait in the first aspect when executing, and the processing method includes the following steps:
s1, the wind control decision system determines to use credit information and credit variables of the applicant;
s2, the wind control decision system sends a request to the data platform or the people 'S bank credit docking platform to obtain a people' S bank credit XML message;
s3 integrating credit investigation SDKs through a data platform or other systems;
s4, the credit investigation SDK is exposed to the outside, the API transmits the personal credit investigation XML message to the API, and the interface returns the credit investigation variable set and the client image code result;
and the S5 data platform transmits the credit investigation variables and the client portrait codes to the wind control decision system to carry out wind control decision or execute related wind control strategies.
Furthermore, in the service processing process, the financial institution can integrate the credit investigation SDK through the data platform, and the data platform firstly calls the personal credit investigation interface to obtain the XML message of the personal credit investigation report.
Further, the calculation of credit derivative variables and the processing logic and strategy of client portrait code are stored in the library of the decision engine platform.
Furthermore, the output parameters of the credit SDK are used as input variables of the decision engine platform.
The invention has the beneficial effects that:
1. when the sizes of the human credit investigation XML message are respectively 20KB (about 800 lines of XML files), 80KB (about 4500 lines of XML files) and 1.7M (about 7 ten thousand lines of XML files), the result shows that all calculation results of the derivative variables can be obtained within 100ms, the processing speed is very high, and the system performance is more than 5 times faster than that of the derivative variables processed based on the database.
2. For the accuracy aspect, the invention continuously corrects the small problems caused by dirty data because the test of variable processing adopts centralized internal test and uses a large amount of real human behavior credit messages to carry out inspection test in the project, thereby effectively ensuring the calculation accuracy aspect.
3. By directly adopting the credit investigation SDK, a financial institution does not need to develop and test a large number of credit investigation derived variables again, and the development and test workload of at least 4 persons per month can be saved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is an interactive architecture diagram of a credit investigation SDK with an associated external system, in accordance with an embodiment of the present invention;
FIG. 2 is a diagram of the steps of a method for service processing in an SDK system based on credit message variable processing and customer representation;
fig. 3 is a functional architecture diagram of the credit investigation SDK system according to the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious 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.
Example 1
The embodiment discloses an SDK system based on credit message variable processing and client portrait, which is shown in fig. 1 and includes,
the personnel credit investigation docking system is used for acquiring a personnel credit investigation request message and respectively acquiring HTML (hypertext markup language) and XML (extensible markup language) formats;
the credit investigation SDK inputs an XML request message of the personal credit investigation at an API interface and outputs a derivative variable containing 200+ credit investigation and a client image code;
the data platform is used for docking an external data source and transmitting data to the analysis library for data analysis;
and the IDE of the decision engine platform is used for realizing the writing and rule strategy configuration of the derived variable function.
The internal module of the credit investigation SDK develops a processing function of a derivative variable based on a decision engine platform and determines the image code of a client based on a strategy by configuring a rule set.
The image codes of the customers represent customers with different customer group classifications or risks, and the generated derivative variables are derivative variables commonly used in daily risk strategies.
The IDE of the decision engine can realize the compiling of the derived variable function and the rule strategy configuration, and is packaged into a software package during software running, wherein the software package is a compiled program.
The software package is embedded in the credit investigation SDK, and the software package runs in the process of the credit investigation SDK when being executed and is executed in the memory.
The software packages are all executed in the memory and do not relate to IO operation of the database.
In the embodiment, a human behavior credit report-based original XML message is adopted, a large number of derived variables are directly processed in a decision engine, and the human behavior derived variables are directly obtained in a manner that an API (application program interface) is exposed to the outside through an SDK (software development kit), so that the repeated development of the complicated derived variables among different projects is avoided, meanwhile, the test work of the derived variables is time-consuming and has high requirements on the correctness of the computational logic, and a large number of repeated test works are reduced.
Because the SDK is developed on the basis of a decision engine, the input parameters of the SDK are XML original messages of the human credit investigation report, processing calculation is carried out in the decision engine, IO operation of a database layer is not needed, the processing performance of the system is greatly improved, processing of a large number of derived variables can be basically completed within one hundred milliseconds for XML messages with more information, and an upstream system can quickly obtain results of all credit investigation variables.
The calculation of the derived variables and the processing logic and strategy of the client portrait code are stored in a library of a decision engine platform, so that the accumulation and the unified management of enterprise-level knowledge assets are facilitated, the unified maintenance and the effect can be realized for later change and maintenance, and the processing logic of the same variable can be unified in different projects.
And the derived variable results generated based on the SDK can be stored in a database for future risk data analysis and optimization.
Example 2
The embodiment discloses a service processing method of an SDK system based on credit investigation message variable processing and client portrait as shown in fig. 2, which includes the following steps:
s1, the wind control decision system determines to use credit information and credit variables of the applicant;
s2, the wind control decision system sends a request to the data platform or the people 'S bank credit docking platform to obtain a people' S bank credit XML message;
s3 integrating credit investigation SDKs through a data platform or other systems;
s4, the credit investigation SDK is exposed to the outside, the API transmits the personal credit investigation XML message to the API, and the interface returns the credit investigation variable set and the client image code result;
and the S5 data platform transmits the credit investigation variables and the client portrait codes to the wind control decision system to carry out wind control decision or execute related wind control strategies.
In the service processing process, a financial institution can integrate the credit investigation SDK through a data platform, and the data platform firstly calls a personal credit investigation interface to obtain an XML message of a personal credit investigation report.
And calculating credit investigation derived variables and processing logic and strategies of client portrait codes are stored in a library of the decision engine platform. And taking the output parameters of the credit investigation SDK as input variables of the decision engine platform.
When the sizes of the human credit investigation XML messages are 20KB (about 800 lines of XML files), 80KB (about 4500 lines of XML files) and 1.7M (about 7 ten thousand lines of XML files), respectively, the results show that all calculation results of the derivative variables can be obtained within 100ms, the processing speed is very high, and the system performance is more than 5 times faster than that of the derivative variables processed based on the database.
For the accuracy aspect, because the test of variable processing adopts centralized internal test and uses a large amount of real human behavior credit messages to carry out inspection test in the project, the small problems caused by dirty data are continuously corrected, and therefore, the calculation accuracy aspect can be effectively ensured.
By directly adopting the credit investigation SDK of the embodiment, a financial institution does not need to redevelop and test a large number of credit investigation derived variables, and the development and test workload of at least 4 persons per month can be saved.
Example 3
The embodiment discloses a functional design inside a credit investigation SDK system. As shown in fig. 3, the input and output of the API interface of the credit SDK are:
[ INPUT ] an XML request message for pedestrian credit. [ OUTPUT ] contains 200+ credit derivative variables and customer image code
Inside the credit SDK module, a decision engine platform (currently adopting FICO Blaze product) is mainly used for developing a processing function of a plurality of derived variables, and a rule set is configured to determine the image code of a client based on a strategy.
The customer's pictorial code may represent a customer classification or a customer with different levels of risk. The generated derivative variables are the derivative variables commonly used in daily risk strategies, and in the current software version, more than 200 credit derivative variables accumulated by a smart risk expert team are included. Subsequently, it will continue to accumulate and increase successively.
The IDE of the decision engine can realize the compiling of the derived variable function and the rule strategy configuration, and then can be packaged into a software runtime software package (the software package is a compiled program), the software package is embedded in the SDK, and the software package can run in the process of the SDK and is executed in the memory when being executed, and IO operation of the database is not involved, so the execution efficiency is very high.
The list of credit investigation derived variables and customer picture codes output is as follows:
in summary, the invention adopts a way of directly processing a large number of derived variables in a decision engine based on the original XML message of the human investigation report, and directly obtains the human derived variables through the way of externally exposing the API interface of the SDK, thereby avoiding the repeated development of the fussy derived variables among different projects, and simultaneously, the test work of the derived variables is also a very time-consuming work with high requirement on the correctness of the computational logic, and also reduces a large number of repeated test works.
Because the SDK is developed on the basis of a decision engine, the input parameters of the SDK are XML original messages of the human credit investigation report, processing calculation is carried out in the decision engine, IO operation of a database layer is not needed, the processing performance of the system is greatly improved, processing of a large number of derived variables can be basically completed within one hundred milliseconds for XML messages with more information, and an upstream system can quickly obtain results of all credit investigation variables.
The calculation of the derived variables and the processing logic and strategy of the client portrait code are stored in a library of a decision engine platform, so that the accumulation and the unified management of enterprise-level knowledge assets are facilitated, the unified maintenance and the effect can be realized for later change and maintenance, and the processing logic of the same variable can be unified in different projects.
And the derived variable results generated based on the SDK can be stored in a database for future risk data analysis and optimization.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. An SDK system based on credit message variable processing and customer portrait, which is characterized by comprising,
the personnel credit investigation docking system is used for acquiring a personnel credit investigation request message and respectively acquiring HTML (hypertext markup language) and XML (extensible markup language) formats;
the credit investigation SDK inputs an XML request message of the personal credit investigation at an API interface and outputs a derivative variable containing 200+ credit investigation and a client image code;
the data platform is used for docking an external data source and transmitting data to the analysis library for data analysis;
and the IDE of the decision engine platform is used for realizing the writing and rule strategy configuration of the derived variable function.
2. The credit investigation message variable processing and customer representation-based SDK system of claim 1, wherein the module of the credit SDK internally develops a processing function of derived variables based on a decision engine platform and determines the representation code of the customer based on a policy by means of configuring a rule set.
3. The credit investigation message variable processing and customer figure based SDK system of claim 2, wherein the customer figure code represents a customer group classification or a customer with different risk levels, and the derived variables are derived variables commonly used in daily risk policy.
4. The credit investigation message variable processing and customer representation-based SDK system of claim 3, wherein the IDE of the decision engine can implement compilation of derived variable functions and rule policy configuration, and is packaged into a software runtime package, wherein the software package is a compiled program.
5. The credit message variable elaboration and customer representation-based SDK system of claim 4, wherein the software package is embedded in the credit SDK, and wherein the software package itself, when executed, runs in a process of the credit SDK, and wherein the process is executed in memory.
6. The credit message variable elaboration and customer figure-based SDK system of claim 1, wherein the software packages are executed in memory and do not involve IO operations on the database.
7. A service processing method of an SDK system based on credit message variable elaboration and customer representation, the processing method when executed using the SDK system based on credit message variable elaboration and customer representation according to any of claims 1-6, characterized in that the processing method comprises the following steps:
s1, the wind control decision system determines to use credit information and credit variables of the applicant;
s2, the wind control decision system sends a request to the data platform or the people 'S bank credit docking platform to obtain a people' S bank credit XML message;
s3 integrating credit investigation SDKs through a data platform or other systems;
s4, the credit investigation SDK is exposed to the outside, the API transmits the personal credit investigation XML message to the API, and the interface returns the credit investigation variable set and the client image code result;
and the S5 data platform transmits the credit investigation variables and the client portrait codes to the wind control decision system to carry out wind control decision or execute related wind control strategies.
8. The method as claimed in claim 7, wherein in the process of service processing, the financial institution can integrate the credit investigation SDK through a data platform, and the data platform first calls a credit investigation interface to obtain the XML message of the credit investigation report.
9. The credit investigation message variable processing and customer figure based service processing method of the SDK system of claim 7, wherein the credit investigation derived variable calculation and customer figure code processing logic and strategy are stored in the decision engine platform library.
10. The credit investigation message variable processing and customer figure based service processing method of the SDK system of claim 7, wherein the output parameters of the credit SDK are used as input variables of the decision engine platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010711327.5A CN112200652B (en) | 2020-12-02 | 2020-12-02 | SDK system based on credit investigation message variable processing and customer portrait and processing method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010711327.5A CN112200652B (en) | 2020-12-02 | 2020-12-02 | SDK system based on credit investigation message variable processing and customer portrait and processing method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112200652A true CN112200652A (en) | 2021-01-08 |
| CN112200652B CN112200652B (en) | 2022-01-11 |
Family
ID=74005570
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010711327.5A Active CN112200652B (en) | 2020-12-02 | 2020-12-02 | SDK system based on credit investigation message variable processing and customer portrait and processing method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112200652B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170032460A1 (en) * | 2015-07-31 | 2017-02-02 | Ncr Corporation | Extracting behaviors and suggesting behaviors to achieve a desired credit score |
| CN106447434A (en) * | 2016-09-14 | 2017-02-22 | 全联征信有限公司 | Personal credit ecological platform |
| CN107332844A (en) * | 2017-07-03 | 2017-11-07 | 上海路诚数据服务有限公司 | Privacy information application method and personal reference methods of marking |
| CN109559220A (en) * | 2018-11-16 | 2019-04-02 | 深圳前海微众银行股份有限公司 | Collection management method, equipment and computer readable storage medium |
| CN110458693A (en) * | 2019-08-08 | 2019-11-15 | 中国建设银行股份有限公司 | A kind of automatic measures and procedures for the examination and approval of business loan, device, storage medium and electronic equipment |
| CN111798308A (en) * | 2020-07-22 | 2020-10-20 | 睿智合创(北京)科技有限公司 | Comprehensive decision platform based on decision engine and method for scheduling data source by comprehensive decision platform |
| CN111833177A (en) * | 2020-07-08 | 2020-10-27 | 融慧金科金融服务外包（北京）有限公司 | Method and device for selecting variable processing logic |
-
2020
- 2020-12-02 CN CN202010711327.5A patent/CN112200652B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170032460A1 (en) * | 2015-07-31 | 2017-02-02 | Ncr Corporation | Extracting behaviors and suggesting behaviors to achieve a desired credit score |
| CN106447434A (en) * | 2016-09-14 | 2017-02-22 | 全联征信有限公司 | Personal credit ecological platform |
| CN107332844A (en) * | 2017-07-03 | 2017-11-07 | 上海路诚数据服务有限公司 | Privacy information application method and personal reference methods of marking |
| CN109559220A (en) * | 2018-11-16 | 2019-04-02 | 深圳前海微众银行股份有限公司 | Collection management method, equipment and computer readable storage medium |
| CN110458693A (en) * | 2019-08-08 | 2019-11-15 | 中国建设银行股份有限公司 | A kind of automatic measures and procedures for the examination and approval of business loan, device, storage medium and electronic equipment |
| CN111833177A (en) * | 2020-07-08 | 2020-10-27 | 融慧金科金融服务外包（北京）有限公司 | Method and device for selecting variable processing logic |
| CN111798308A (en) * | 2020-07-22 | 2020-10-20 | 睿智合创(北京)科技有限公司 | Comprehensive decision platform based on decision engine and method for scheduling data source by comprehensive decision platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112200652B (en) | 2022-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112394922B (en) | Decision configuration method, business decision method and decision engine system | |
| US20210279612A1 (en) | Computerized System and Method of Open Account Processing | |
| US10579396B2 (en) | System and automated method for configuring a predictive model and deploying it on a target platform | |
| US20090113387A1 (en) | Methods and systems for dynamically generating and optimizing code for business rules | |
| O'Halloran et al. | An artificial intelligence approach to regulating systemic risk | |
| WO2021223215A1 (en) | Automated decision platform | |
| US20160078531A1 (en) | Aggregation engine for real-time counterparty credit risk scoring | |
| CN103455476B (en) | The processing method of the network information and the method for building up of abstract syntax tree and device thereof | |
| Georgakopoulos | Quantitative trading with R: understanding mathematical and computational tools from a quant’s perspective | |
| CN113721898A (en) | Machine learning model deployment method, system, computer device and storage medium | |
| CN112200652B (en) | SDK system based on credit investigation message variable processing and customer portrait and processing method thereof | |
| Mishra | Machine learning for iOS developers | |
| Avdeenko et al. | Intelligent support of requirements management in agile environment | |
| CN112114817B (en) | COBOL language-based data dictionary field information acquisition method and device | |
| CN110502483B (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN110633077B (en) | Quick development system and method based on modularization | |
| Conlan | Automated Trading with R | |
| CN112612481A (en) | System architecture of intelligent middle station | |
| Chancelier et al. | Using Premia and Nsp for constructing a risk management benchmark for testing parallel architecture | |
| CN113704618B (en) | Data processing method, device, equipment and medium based on deep learning model | |
| Fibla Salgado | A web scraping framework for stock price modelling using deep learning methods | |
| EP4350582A1 (en) | Machine learning program, machine learning method, and information processing apparatus | |
| US20240152805A1 (en) | Systems, methods, and non-transitory computer-readable storage devices for training deep learning and neural network models using overfitting detection and prevention | |
| Meliones et al. | Automated Stock Price Motion Prediction Using Technical Analysis Datasets and Machine Learning | |
| Helskyaho et al. | Delivery and Automation Pipeline in Machine Learning |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |