CN113657904A - Chemical transaction risk assessment method and system - Google Patents

Chemical transaction risk assessment method and system Download PDF

Info

Publication number
CN113657904A
CN113657904A CN202110942185.8A CN202110942185A CN113657904A CN 113657904 A CN113657904 A CN 113657904A CN 202110942185 A CN202110942185 A CN 202110942185A CN 113657904 A CN113657904 A CN 113657904A
Authority
CN
China
Prior art keywords
risk
transaction
order
chemical
risk assessment
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
Application number
CN202110942185.8A
Other languages
Chinese (zh)
Inventor
朱剑川
谢道德
肖建峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xiamen Huiyintongda Digital Technology Co ltd
Original Assignee
Xiamen Huiyintongda Digital Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xiamen Huiyintongda Digital Technology Co ltd filed Critical Xiamen Huiyintongda Digital Technology Co ltd
Priority to CN202110942185.8A priority Critical patent/CN113657904A/en
Publication of CN113657904A publication Critical patent/CN113657904A/en
Pending legal-status Critical Current

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
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G06Q20/401—Transaction verification
    • G06Q20/4016—Transaction verification involving fraud or risk level assessment in transaction processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • 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
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
    • G06Q30/0635—Processing of requisition or of purchase orders
    • 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
    • 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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Software Systems (AREA)
  • Development Economics (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Technology Law (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • Manufacturing & Machinery (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Primary Health Care (AREA)
  • Tourism & Hospitality (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the technical field of computers, in particular to a chemical transaction risk assessment method and a chemical transaction risk assessment system, wherein the method adopts data in a historical data set to carry out mathematical modeling, establishes a prediction model through machine learning, and inputs order parameters into the prediction model to calculate and obtain a risk coefficient; selecting different transaction modes for transaction according to the risk coefficients; according to the invention, the transaction records are subjected to risk assessment based on a machine learning means, so that the transaction risk and the generation of bad accounts can be effectively reduced; the risk assessment is improved from the original manual experience operation, and is upgraded into historical data-based assessment prediction, so that the method is better, objective, efficient and accurate; competitive advantages can be effectively improved through the prediction model, and service expansion and resource reuse are improved.

Description

Chemical transaction risk assessment method and system
Technical Field
The invention relates to the technical field of computers, in particular to a chemical transaction risk assessment method and system.
Background
The transportation of the chemical industry is still in a relatively laggard stage of informatization development at present, the sold commodities are often large in amount, not timely in inventory scheduling, delinquent in goods payment and the like, the risk assessment and processing performed manually are not only low in efficiency, but also easy to make mistakes, and the risk is high for the bulk commodities of the chemical industry and the like.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the chemical transaction risk assessment method and the system for risk assessment of commodities, customers, warehouses and funds involved in the process of selling the bulk chemical commodities are provided.
In order to solve the technical problems, the invention adopts the technical scheme that:
a chemical transaction risk assessment method comprises
Establishing a prediction model through machine learning after performing mathematical modeling by adopting data in a historical data set, and inputting order parameters into the prediction model to calculate to obtain a risk coefficient;
the calculation method of the risk coefficient comprises the following steps:
Figure BDA0003215313400000011
and selecting different transaction modes for transaction according to the risk coefficients.
In order to solve the technical problem, the invention adopts another technical scheme as follows:
a chemical transaction risk assessment system comprises
The operation terminal is used for preparing an order with order parameters and transmitting the order to the order risk evaluation system;
the order risk evaluation system extracts order parameters in the order, sends the order parameters into the prediction model and selects different transaction modes to carry out transaction with the operation terminal according to the returned risk coefficients; and the prediction model is used for evaluating the order parameters and generating corresponding risk coefficients to be returned to the order risk evaluation system.
The invention has the beneficial effects that: by carrying out risk assessment on the transaction records based on a machine learning means, the transaction risk and the generation of bad accounts can be effectively reduced; the risk assessment is improved from the original manual experience operation, and is upgraded into historical data-based assessment prediction, so that the method is better, objective, efficient and accurate; the data source of the method is based on a free online transaction platform (the operation end can be communicated with the order risk assessment system through the Internet), the competitive advantage can be effectively improved through a prediction model, and the service expansion and the resource reuse are improved.
Drawings
Fig. 1 is a logic framework diagram of a chemical transaction risk assessment method according to an embodiment of the present invention.
Detailed Description
In order to explain technical contents, achieved objects, and effects of the present invention in detail, the following description is made with reference to the accompanying drawings in combination with the embodiments.
Referring to fig. 1, a method for assessing risk of chemical transaction includes
Establishing a prediction model through machine learning after performing mathematical modeling by adopting data in a historical data set, and inputting order parameters into the prediction model to calculate to obtain a risk coefficient;
the calculation method of the risk coefficient comprises the following steps:
Figure BDA0003215313400000021
and selecting different transaction modes for transaction according to the risk coefficients.
Further, the step of selecting different transaction modes for transaction according to the risk coefficient comprises the steps of judging whether the risk coefficient is larger than or equal to 90, if so, regarding the order corresponding to the order parameter as a high risk, and refusing to put in credit or pay for goods; if not, judging whether the risk coefficient is more than or equal to 80 and less than 90, if so, regarding the order corresponding to the order parameter as moderate risk, allowing payment of partial loan, and paying a tail payment after delivery; if not, whether the risk coefficient is less than 80 is judged, and the order corresponding to the order parameter is regarded as low-degree risk, and the payment is allowed.
Further, the historical data set includes: customer purchase records, customer recharge records and amounts, customer default records, and customer credit, reputation, enterprise size.
Further, before mathematical modeling, the historical data set is cleaned by an ETL method, and the data is queried, de-duplicated, aggregated, counted and screened to obtain the concerned core fields and data.
As can be seen from the above description, ETL is an abbreviation of Extract-Transform-Load by the ETL method, and processes of data extraction (Extract), transformation (Transform), and loading (Load).
Further, the machine learning adopts a multi-label decision tree learning algorithm to learn, and a trend graph of a historical data set is calculated in a matched manner through statistics to train.
From the above description, it can be known that machine learning comparison extraction reference can be facilitated through the trend graph.
Further, the transaction is added to the historical data set after the transaction is completed.
As can be seen from the above description, data is also recorded as a historical data set.
A chemical transaction risk assessment system comprises
The operation terminal is used for preparing an order with order parameters and transmitting the order to the order risk evaluation system;
the order risk evaluation system extracts order parameters in the order, sends the order parameters into the prediction model and selects different transaction modes to carry out transaction with the operation terminal according to the returned risk coefficients; and
and the prediction model is used for evaluating the order parameters and generating corresponding risk coefficients to be returned to the order risk evaluation system.
Further, the order risk evaluation system receives the returned risk coefficient, judges whether the risk coefficient is more than or equal to 90, if so, the order corresponding to the order parameter is regarded as high risk, and refuses to put in credit or pay for goods; if not, judging whether the risk coefficient is more than or equal to 80 and less than 90, if so, regarding the order corresponding to the order parameter as moderate risk, allowing payment of partial loan, and paying a tail payment after delivery; if not, whether the risk coefficient is less than 80 is judged, and the order corresponding to the order parameter is regarded as low-degree risk, and the payment is allowed.
Further, the order parameters include the goods purchased, quantity, area and warehousing address.
Further, the order risk assessment system adds the transaction to the historical data set after the transaction is completed.
From the above description, the risk assessment is performed on the transaction records based on the machine learning means, so that the transaction risk and the generation of bad accounts can be effectively reduced; the risk assessment is improved from the original manual experience operation, and is upgraded into historical data-based assessment prediction, so that the method is better, objective, efficient and accurate; the data source of the method is based on a free online transaction platform (the operation end can be communicated with the order risk assessment system through the Internet), the competitive advantage can be effectively improved through a prediction model, and the service expansion and the resource reuse are improved.
Example one
A chemical transaction risk assessment method comprises
Establishing a prediction model through machine learning after performing mathematical modeling by adopting data in a historical data set, and inputting order parameters into the prediction model to calculate to obtain a risk coefficient;
the calculation method of the risk coefficient comprises the following steps:
Figure BDA0003215313400000041
and selecting different transaction modes to carry out transaction according to the risk coefficients, and adding the transaction (including orders, order parameters, transaction time, fulfillment and the like) into the historical data set (for feedback) after the transaction is completed.
Wherein
The step of selecting different transaction modes for transaction according to the risk coefficients comprises the steps of judging whether the risk coefficients are more than or equal to 90, if so, regarding the order corresponding to the order parameters as a high risk, and refusing to put in credit or pay by delivery; if not, judging whether the risk coefficient is more than or equal to 80 and less than 90, if so, regarding the order corresponding to the order parameter as moderate risk, allowing payment of partial loan, and paying a tail payment after delivery; if not, whether the risk coefficient is less than 80 is judged, and the order corresponding to the order parameter is regarded as low-degree risk, and the payment is allowed.
The historical data set includes: customer purchase records, customer recharge records and amounts, customer default records, and customer credit, reputation, enterprise size.
Before mathematical modeling is carried out on the historical data set, data in the historical data set are cleaned by an ETL (extraction-transformation-Loading) method, and the data are inquired, deduplicated, aggregated, counted and screened to obtain concerned core fields and data.
The machine learning adopts a multi-label decision tree learning algorithm to learn, and is trained by matching with a trend graph (such as statistical maximum, minimum, average, mode, median and the like which can form a graph) of a historical data set counted by statistics.
Example two
A chemical transaction risk assessment system comprises
The operation terminal is used for preparing an order with order parameters and transmitting the order to the order risk evaluation system through the Internet (http protocol);
the order risk evaluation system extracts order parameters in the order, sends the order parameters into the prediction model and selects different transaction modes to carry out transaction with the operation terminal according to the returned risk coefficients; the order risk evaluation system receives the returned risk coefficient, judges whether the risk coefficient is more than or equal to 90, if so, the order corresponding to the order parameter is regarded as high risk, and refuses to put in credit or pay by delivery; if not, judging whether the risk coefficient is more than or equal to 80 and less than 90, if so, regarding the order corresponding to the order parameter as moderate risk, allowing payment of partial loan, and paying a tail payment after delivery; if not, whether the risk coefficient is less than 80 is judged, and the order corresponding to the order parameter is regarded as low-degree risk, and the payment is allowed.
And the prediction model is used for evaluating the order parameters and generating corresponding risk coefficients to be returned to the order risk evaluation system.
Wherein
The order parameters include the goods purchased, quantity, area, and warehousing address.
The order risk assessment system adds the trade (including the order, order parameters, time of trade, fulfillment, etc.) to the historical data set after the trade is complete.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all equivalent changes made by using the contents of the present specification and the drawings, or applied directly or indirectly to the related technical fields, are included in the scope of the present invention.

Claims (10)

1. A chemical transaction risk assessment method is characterized by comprising
Establishing a prediction model through machine learning after performing mathematical modeling by adopting data in a historical data set, and inputting order parameters into the prediction model to calculate to obtain a risk coefficient;
the calculation method of the risk coefficient comprises the following steps:
Figure FDA0003215313390000011
and selecting different transaction modes for transaction according to the risk coefficients.
2. The chemical transaction risk assessment method according to claim 1, wherein the "selecting different transaction modes for transaction according to the risk coefficient" comprises judging whether the risk coefficient is greater than or equal to 90, if so, regarding the order corresponding to the order parameter as a high risk, and refusing to put in credit or pay for goods; if not, judging whether the risk coefficient is more than or equal to 80 and less than 90, if so, regarding the order corresponding to the order parameter as moderate risk, allowing payment of partial loan, and paying a tail payment after delivery; if not, whether the risk coefficient is less than 80 is judged, and the order corresponding to the order parameter is regarded as low-degree risk, and the payment is allowed.
3. The chemical transaction risk assessment method of claim 1, wherein the historical data set comprises: customer purchase records, customer recharge records and amounts, customer default records, and customer credit, reputation, enterprise size.
4. The chemical transaction risk assessment method according to claim 1, wherein the historical data set is cleaned by an ETL method before being subjected to mathematical modeling, and the data is subjected to query, deduplication, aggregation, statistics and screening to obtain core fields and data concerned.
5. The chemical transaction risk assessment method according to claim 1, wherein the machine learning employs a multi-label decision tree learning algorithm for learning, and is trained in cooperation with a trend graph of a historical data set statistically counted.
6. The chemical transaction risk assessment method of claim 1, wherein the transaction is added to the historical data set after completion of the transaction.
7. A chemical transaction risk assessment system is characterized by comprising
The operation terminal is used for preparing an order with order parameters and transmitting the order to the order risk evaluation system;
the order risk evaluation system extracts order parameters in the order, sends the order parameters into the prediction model and selects different transaction modes to carry out transaction with the operation terminal according to the returned risk coefficients; and
and the prediction model is used for evaluating the order parameters and generating corresponding risk coefficients to be returned to the order risk evaluation system.
8. The chemical transaction risk assessment system according to claim 7, wherein the order risk assessment system receives the returned risk coefficient, determines whether the risk coefficient is greater than or equal to 90, and if so, the order corresponding to the order parameter is regarded as a high risk, and refuses to put in credit or pay for goods; if not, judging whether the risk coefficient is more than or equal to 80 and less than 90, if so, regarding the order corresponding to the order parameter as moderate risk, allowing payment of partial loan, and paying a tail payment after delivery; if not, whether the risk coefficient is less than 80 is judged, and the order corresponding to the order parameter is regarded as low-degree risk, and the payment is allowed.
9. The chemical transaction risk assessment system of claim 7, wherein the order parameters include goods purchased, quantity, region, and warehousing address.
10. The chemical transaction risk assessment system of claim 7, wherein the order risk assessment system adds the transaction to the historical data set after the transaction is completed.
CN202110942185.8A 2021-08-17 2021-08-17 Chemical transaction risk assessment method and system Pending CN113657904A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110942185.8A CN113657904A (en) 2021-08-17 2021-08-17 Chemical transaction risk assessment method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110942185.8A CN113657904A (en) 2021-08-17 2021-08-17 Chemical transaction risk assessment method and system

Publications (1)

Publication Number Publication Date
CN113657904A true CN113657904A (en) 2021-11-16

Family

ID=78479891

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110942185.8A Pending CN113657904A (en) 2021-08-17 2021-08-17 Chemical transaction risk assessment method and system

Country Status (1)

Country Link
CN (1) CN113657904A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115170304A (en) * 2022-06-22 2022-10-11 支付宝(杭州)信息技术有限公司 Method and device for extracting risk feature description
CN118171921A (en) * 2024-05-15 2024-06-11 杭州小策科技有限公司 Risk intelligent insight method and system for multi-source data

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115170304A (en) * 2022-06-22 2022-10-11 支付宝(杭州)信息技术有限公司 Method and device for extracting risk feature description
CN115170304B (en) * 2022-06-22 2023-03-28 支付宝(杭州)信息技术有限公司 Method and device for extracting risk feature description
CN118171921A (en) * 2024-05-15 2024-06-11 杭州小策科技有限公司 Risk intelligent insight method and system for multi-source data

Similar Documents

Publication Publication Date Title
CN110348963B (en) Method and system for realizing intelligent transaction recommendation of multiple commodities for transaction platform
JP3481570B2 (en) Demand forecasting equipment in parts inventory management
CN113657904A (en) Chemical transaction risk assessment method and system
US20120278205A1 (en) Vertical Network Computing Integration, Analytics, And Automation
CN106651402A (en) Data processing method for goods return operation
CN101655948A (en) Online trading method and online trading system
CN110930221B (en) Abnormal order processing method, storage medium and computer equipment
CN112184348B (en) Order data processing method, device, electronic equipment and medium
US20150363855A1 (en) Systems and Methods for Automatic Popular Configuration Generation
CN108182575A (en) A kind of realization system and method for the multi-party income real time settlement of internet electric business
US20190236694A1 (en) Predictive risk management for supply chain receivables financing
KR102199852B1 (en) Private trading system of waste resources and its method
CN108681957B (en) Cross-border e-commerce transaction order restoration method, system, equipment and storage medium
CN115545757A (en) Behavior data intelligent simulation method for E-commerce transaction subject
US20100153241A1 (en) System and method for automated reconciliation of purchase orders
Lee et al. E-commerce supply chain network design using on-demand warehousing system under uncertainty
CN114610768A (en) Cross-border commodity information processing method and device
US20050288962A1 (en) Method for effecting customized pricing for goods or services
Ouyang et al. An integrated inventory model with quality improvement and two-part credit policy
CN112669115A (en) Bulk commodity matching transaction system and method
Campos-Garcia et al. Relationship between cost and logistic practices in small and medium enterprises: A case study of Queretaro, Mexico
JP2017208090A (en) Information processing device
KR101587325B1 (en) Intellectual property right collateral loan method and server performing the same
Utami et al. An integrated inventory model for deteriorated and imperfect items considering carbon emissions and inflationary environment
Kébé et al. A Lagrangean heuristic for a two-echelon storage capacitated lot-sizing problem

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20211116