CN118967294A

CN118967294A - A risk warning method and related device

Info

Publication number: CN118967294A
Application number: CN202410913560.XA
Authority: CN
Inventors: 卓亮亮; 林巧; 王霞
Original assignee: Maibao Yunshu Shenzhen Technology Co ltd
Current assignee: Maibao Yunshu Shenzhen Technology Co ltd
Priority date: 2024-07-09
Filing date: 2024-07-09
Publication date: 2024-11-15

Abstract

The embodiment of the present application discloses a risk warning method and related devices, the method comprising: obtaining store operation data of the subject to be evaluated; inputting the store operation data into a compliance risk model to obtain a compliance risk score; inputting the store operation data into an operating risk model to obtain an operating risk score; and outputting risk warning information based on the compliance risk score and the operating risk score. The embodiment of the present application can more accurately evaluate the compliance risk and operating risk of the subject to be evaluated, thereby helping financial institutions make more reasonable loan decisions during credit approval, and timely warning when the lending risk or repayment risk is high.

Description

Risk early warning method and related device

Technical Field

The invention relates to the technical field of financial risk control, in particular to a risk early warning method and a related device.

Background

The cross-border e-commerce (hereinafter referred to as cross-border e-commerce) refers to transaction subjects belonging to different environments, and achieves transaction, electronic payment settlement through an e-commerce platform, and commodity delivery through cross-border e-commerce logistics and off-site storage, so that the international business activity of the transaction is completed.

The cross-border electronic business has the characteristics of less flowing funds, long goods money recycling period, money exchange loss, longer export tax return period, electronic business platform funds occupation and the like, and enterprises of the main cross-border electronic business often need to carry out funds turnover by means of loan business of financial institutions, so that higher requirements are put on the wind control technology of the financial institutions.

Currently, financial institutions perform risk assessment by credit status, financial status, value of the security articles, etc. of borrowers. However, due to privacy data protection policies of various countries, it is difficult for financial institutions to acquire transaction data from overseas electronic commerce platforms to audit finances of overseas portions of cross-border electronic commerce businesses; meanwhile, most of the cross-border electronic commerce enterprises are insufficient in guarantee articles to support the lending application. These circumstances lead to financial institutions having difficulty in accurately assessing the lending risk of cross-border e-commerce enterprises, and more conservative payment decisions, thereby affecting the development of cross-border e-commerce enterprises.

Based on the above background, there is a need for a risk early warning method to help financial institutions perform risk early warning when conducting credit approval and post-loan monitoring on small and medium enterprises in cross-border electronic commerce.

Disclosure of Invention

The embodiment of the invention provides a risk early warning method and a related device, which can more accurately evaluate the lending risk of cross-border electronic commerce enterprises and early warn in the scene that financial institutions carry out credit approval and post-lending monitoring on the small enterprises in the cross-border electronic commerce.

The first aspect of the embodiment of the application provides a risk early warning method which is applied to computing equipment; the method comprises the following steps: acquiring store operation data of a subject to be evaluated; inputting the store operation data into a compliance risk model to obtain a compliance risk score; inputting the store business data into a business risk model to obtain a business risk score; and outputting risk early warning information based on the compliance risk score and the business risk score.

In the embodiment of the application, based on the store operation data of the main body to be evaluated, the compliance risk and the operation risk of the main body to be evaluated can be evaluated more accurately by performing evaluation calculation through the compliance risk model and the operation risk model, thereby helping financial institutions to make more reasonable payment decisions during credit giving and approval and giving early warning in time when the lending risk or the withdrawal risk is larger.

In one possible implementation, after the acquiring the store operation data of the subject to be evaluated, the method further includes: calculating a scale level of the store of the subject to be evaluated based on the store business data, and first derivative data and second derivative data, wherein the first derivative data is data required for the calculation of the compliance risk model, and the second derivative data is data required for the calculation of the business risk model; the store operation data is input into a compliance risk model to obtain a compliance risk score, which comprises the following steps: inputting the first derivative data and the scale level into the compliance risk model, and calculating based on the evaluation standard corresponding to the scale level through the compliance risk model to obtain the compliance risk score; the store management data is input into a management risk model to obtain a management risk score, which comprises the following steps: and inputting the second derivative data and the scale level into the operation risk model, and calculating based on the evaluation standard corresponding to the scale level through the operation risk model to obtain the operation risk score.

In the embodiment of the application, the derivative data is obtained by preprocessing the store operation data, so that the calculation processing of the compliance risk model and the operation risk model is more convenient; meanwhile, the scale level of the store is determined through store operation data, and then the corresponding evaluation standard is adopted for calculation and evaluation, so that the evaluation mode is more flexible, and the related risks of stores with different scales can be evaluated more accurately.

In one possible implementation, the store operating data includes a platform score and sales of a secondary store, which is a child of a primary store, and sales of a primary store; the store operation data is input into a compliance risk model to obtain a compliance risk score, which comprises the following steps: inputting the platform score and sales of the secondary store and sales of the primary store into the compliance risk model, and calculating the compliance score of the corresponding primary store based on the platform score of the secondary store and the ratio of the sales of the secondary store to the sales of the corresponding primary store through the compliance risk model; and calculating the compliance risk score based on the compliance score and sales of the first store of the subject to be evaluated through the compliance risk model.

The platform score is the policy compliance score of the electric Shang Ping of the secondary store to the secondary store.

In the embodiment of the application, the compliance risk score of the store of the main body to be evaluated can be calculated through the platform score and sales amount, so that the compliance risk of the store on the electronic commerce platform can be accurately evaluated and measured.

In one possible implementation, the business risk model comprises a water line model, and the store business data comprises inventory value, amount to be refunded, return rate, refund rate, in-transit funds, and reserved amount; before the store business data is input into the business risk model to obtain the business risk score, the method further comprises: acquiring the on-credit amount of the subject to be evaluated; the store management data is input into a management risk model to obtain a management risk score, which comprises the following steps: inputting the inventory value, the amount to be refunded, the return rate, the refund rate, the in-transit funds and the reserved amount into the water line model, and calculating to obtain receivables through the water line model; inputting the on-credit into the water line model, and obtaining a first score based on the ratio of the receivables to the on-credit through the water line model; the business risk score is calculated based on the first score.

According to the embodiment of the application, the repayment capability of the main body to be evaluated can be accurately evaluated by calculating the proportion between the receivables and the credits of the main body to be evaluated, so that early warning can be timely carried out on financial institutions when the repayment capability of the main body to be evaluated is insufficient.

In one possible implementation, the business risk model comprises a cash flow stabilization model, and the store business data comprises a store daily sales amount; the store management data is input into a management risk model to obtain a management risk score, which comprises the following steps: inputting the sales of the shops into the cash flow stabilizing model, calculating the sum of sales of the shops in the last week and the average value of the sales of the lowest N shops in the last year through the cash flow stabilizing model, wherein N is an integer greater than 1; obtaining a second score based on a ratio of a sum of sales of store days of the last week to the average value by the cash flow stabilization model; the business risk score is calculated based on the second score.

In the embodiment of the application, the sales change and the operating condition of the store can be accurately estimated by comparing the latest weekly sales of the store with the average value of the lower daily sales.

In one possible implementation, the business risk model comprises a warehouse clearance risk model, the store business data comprises a quantity and price of the individual items, the individual items comprising warehouse clearance individual items; the store management data is input into a management risk model to obtain a management risk score, which comprises the following steps: inputting the quantity and the price of the single products into the warehouse-clearing risk model, calculating the total value of the warehouse-clearing single products based on the quantity and the price of the warehouse-clearing single products through the warehouse-clearing risk model, and calculating the total value of all the single products based on the quantity and the price of all the single products; obtaining a third score based on the ratio of the total value of the warehouse-removed individual items to the total value of all individual items through the warehouse-removed risk model; the business risk score is calculated based on the third score.

In the embodiment of the application, whether the corresponding store is a warehouse-clearing store or not is judged through the ratio of the total value of warehouse-clearing single products to the total value of all single products, so that the operation condition and the warehouse-clearing risk of the store can be accurately evaluated.

In one possible implementation, before the inputting the store business data into the business risk model, the method further comprises: if the proportion of the used goods of the single product is greater than a first threshold value and the sale discount in the last three months is greater than a second threshold value, determining that the single product is a warehouse-removed single product, wherein the proportion of the used goods is the ratio of the number of the single products to the total number of the single products in the warehouse time of more than 180 days.

Wherein the second threshold is an average discount off sales for the same or similar items over the same period of time.

According to the embodiment of the application, the discount and inventory conditions of the single products of the store are monitored in real time, and the average discount level of similar products at the same time is compared, so that the management condition and the warehouse clearance risk of the store can be accurately identified.

A second aspect of an embodiment of the present application provides a risk early warning device, including: the acquisition module is used for acquiring store operation data of the main body to be evaluated; the first evaluation module is used for inputting the store operation data into a compliance risk model to obtain a compliance risk score; the second evaluation module is used for inputting the store management data into the management risk model to obtain a management risk score; and the early warning module is used for outputting risk early warning information based on the compliance risk score and the management risk score.

A third aspect of an embodiment of the application provides a computing device, wherein the computing device includes a memory and a processor; the memory is coupled to the processor; the memory is used for storing computer program instructions; the processor is configured to invoke the computer program instructions to perform the method as described in any of the possible implementations of the first aspect.

A fourth aspect of the embodiment of the present application provides a computer-readable storage medium, wherein computer-executable instructions are stored in the computer-readable storage medium; wherein the computer-executable instructions, when executed by a processor, implement a method as may be implemented in any one of the first aspects.

It should be appreciated that the benefits of the various aspects described above may be referenced to one another.

Drawings

In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic flow chart of a risk early warning method according to an embodiment of the present application;

FIG. 2 is a data flow chart of another risk early warning process according to an embodiment of the present application;

Fig. 3 is a schematic structural diagram of a risk early warning device according to an embodiment of the present application;

fig. 4 is a block diagram of a computing device according to an embodiment of the present application.

Detailed Description

For the purpose of illustrating embodiments of the application, there is shown in the drawings, embodiments which are described herein, some, but not all embodiments of the application. As one of ordinary skill in the art can know, with the development of technology and the appearance of new scenes, the technical scheme provided by the embodiment of the application is also applicable to similar technical problems.

The terms first, second and the like in the description and in the claims and in the above-described figures, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

The embodiment of the application provides a risk early warning method for solving the problem that the lending risk assessment accuracy of cross-border electronic commerce enterprises is low in the scene that financial institutions carry out credit approval and post-lending monitoring on small enterprises in the cross-border electronic commerce enterprises.

Referring to fig. 1, fig. 1 is a flowchart of a risk early warning method according to an embodiment of the present application, where the method is applied to a computing device, and the method specifically includes steps 102 to 108.

Step 102, the computing device obtains store operation data of the subject to be evaluated.

The subject to be evaluated is an e-commerce enterprise, and may specifically be a cross-border e-commerce enterprise. In this embodiment, a main body to be evaluated is taken as a cross-border e-commerce enterprise as an example.

The store operation data refer to data generated in the operation process of stores opened by electronic business enterprises on various electronic business platforms. By way of example, store operating data may include individual item numbers, individual item prices, quantity in store, quantity of order deals, time of transaction, rate of returns, sales over different time periods, and so forth.

It can be understood that an e-commerce enterprise can simultaneously set up e-commerce shops (hereinafter referred to as shops) on a plurality of e-commerce platforms, and can also simultaneously operate a plurality of brands on the same e-commerce platform; furthermore, each brand can also respectively establish stores of different types, for example, a television store and a kitchen appliance store are simultaneously opened under the appliance brand. For ease of illustration, the relationship is described herein using a primary store and a secondary store, the secondary store being a child of the primary store, the subject to be evaluated may possess one or more primary stores, and the primary store may include one or more secondary stores.

In the scenario that the financial institution performs credit approval and post-loan monitoring, the computing device of the financial institution can access an e-commerce platform where the store of the subject to be evaluated is located, and obtain relevant data of the corresponding store through an application programming (application programming interface, API) interface of the e-commerce platform after the subject to be evaluated is authorized.

Specifically, the computing device may clean and process the acquired data into store operation data that is easy to interpret and store.

In one possible implementation, after the acquiring the store operating data of the subject to be evaluated, the computing device may calculate a scale level of the store of the subject to be evaluated, and the first derivative data and the second derivative data based on the store operating data, before performing steps 104 and 106.

Wherein the scale level of the store is used to determine the assessment criteria for the compliance risk model and the business risk model. It will be appreciated that different scale stores may require different assessment criteria to calculate risk.

For example, the computing device may calculate a total amount of commodity transactions (gross merchandise volume, GMV) for the corresponding store in the last year, half year, or quarter based on the store operational data, and then determine a scale level for the store based on the GMV.

Wherein the first derivative data is data required for the compliance risk model calculation and the second derivative data is data required for the business risk model calculation.

The computing equipment can process according to the acquired original shop data to obtain derivative data corresponding to derivative indexes required by different risk models. For example, the computing device may count the fees for each order to obtain sales for each order; all time-related indexes can also be calculated from the time dimension, such as the return amount of 12 natural months and the return sales amount of 3 natural months; statistics can also be performed from a summary perspective, such as the total sales of all stores authorized under the subject to be assessed over the last 12 natural months, the inventory value of the subject to be assessed's overall inventory, etc.

Different risk models may require data of different dimensions, and the data required by the compliance risk model and the management risk model are obtained by preprocessing store operation data, so that subsequent calculation of the risk model is facilitated.

And 104, the computing equipment inputs the store operation data into the compliance risk model to obtain a compliance risk score.

The compliance risk model is used for evaluating the compliance risk of a store of a subject to be evaluated, and the compliance risk score is used for indicating the magnitude of the compliance risk of the store. The compliance risk in the document of the present application refers to the risk that a store of an e-commerce platform may suffer legal sanctions or regulatory penalties, significant financial losses or reputation losses due to failure to comply with legal regulations, regulatory requirements, rules, related guidelines established by the automated organization, and behavioral guidelines applicable to the e-commerce activity.

Specifically, the compliance risk model calculates a compliance risk score based on compliance-related data of the store of the subject to be evaluated. Illustratively, the compliance-related data may include a penalty record for the store, and may also include a policy compliance score for the store by the e-commerce platform, such as an account status rating (AHR) of the amazon e-commerce platform.

It will be appreciated that depending on the calculation rules, there may be a higher compliance risk score. The smaller the compliance risk; there may be situations where the lower the compliance risk score, the smaller the compliance risk, and embodiments of the present application are not specifically limited herein.

In one possible implementation, the computing device inputs the first derivative data and the scale level into a compliance risk model, and calculates the compliance risk score based on an evaluation criterion corresponding to the scale level through the compliance risk model.

The computing device inputs first derivative data of each store, scale level and corresponding relation of the first derivative data and the scale level into the compliance risk model at the same time. Illustratively, the first derivative data of each store is labeled, and the compliance risk model may calculate a compliance risk score using corresponding evaluation criteria via scale level labeling of the first derivative data.

In another possible implementation, the operation of computing the first derivative data based on the raw data may be performed by a compliance risk model.

After obtaining the data required for the calculation, the computing device may calculate a compliance risk score via the compliance risk model.

In one possible implementation, the store operating data includes a platform score and sales of the secondary store, and sales of the primary store; the computing equipment inputs the platform score and sales of the secondary store and sales of the primary store into the compliance risk model, and calculates the compliance score corresponding to the primary store based on the platform score of the secondary store and the ratio of the sales of the secondary store to the sales of the primary store through the compliance risk model; and then calculating the compliance risk score based on the compliance score and sales of the first store of the subject to be evaluated through the compliance risk model.

The platform score is the policy compliance score of the electric Shang Ping of the secondary store to the secondary store. Illustratively, the platform score may be the AHR of the amazon e-commerce platform.

For example, the compliance risk model may perform a weighted average calculation on the platform scores of secondary stores belonging to the same primary store and the sales occupancy to obtain the compliance score of the corresponding primary store. If the primary store belongs to secondary stores A and B, the sales of A is 300 ten thousand, and the platform score is 1000; b is sold at 200 ten thousand and the platform score is 500, the weighted average can calculate 300 ten thousand/500 ten thousand 1000+200 ten thousand/500 ten thousand 500=800, resulting in a compliance score of 800 for the primary store.

For example, the compliance risk model may perform weighted average calculation on the compliance scores and sales percentages of all primary shops of the subject to be evaluated based on the same rule, to obtain the compliance risk score.

It can be understood that, under the condition that all primary shops of the main body to be evaluated are on the same electronic commerce platform, the compliance score of each primary shop can adopt the same threshold standard to judge the magnitude of the compliance risk, and the compliance risk model can directly perform the weighted average calculation to obtain the compliance risk score; under the condition that the primary shops of the main body to be evaluated are on different electronic commerce platforms, the compliance risk model needs to convert the compliance scores of the primary shops into scores under a unified standard, and then the compliance risk scores of the main body to be evaluated are obtained based on the weighted average calculation of the sales occupancy ratio.

In another possible implementation, the store operating data includes historical penalty data and/or policy compliance deduction data for the store from an e-commerce platform where the store is located; the compliance risk model may calculate a compliance score for the store based on the historical penalty data and/or policy compliance points data; and obtaining the compliance risk score of the subject to be evaluated based on weighted average calculation of the compliance score and sales ratio of each store.

The compliance risk model may be a deduction system, and each time a store has a history punishment item or a policy compliance deduction item, the score corresponding to the item is deducted, so as to obtain a compliance score of the store.

And 106, the computing equipment inputs the store business data into a business risk model to obtain a business risk score.

The management risk model is used for evaluating the management risk of the store of the subject to be evaluated, and the management risk score is used for indicating the size of the management risk of the store. The business risk in the document of the present application refers to the possibility that the future business cash flow of the enterprise changes due to production business variations or market environment changes, thereby affecting the market value and repayment capability of the subject to be evaluated.

Specifically, the management risk model can evaluate the management risk of the store through data of multiple dimensions, such as whether goods backlog exists or not, and the risk of warehouse clearance is needed; or less receivables and insufficient repayment capacity.

In one possible implementation, the computing device inputs the second derivative data and the scale level into an operational risk model, and calculates the operational risk score based on the evaluation criteria corresponding to the scale level through the operational risk model.

This possible implementation is similar to the possible implementation of the computing device entering the first derivative data and scale level into the compliance risk model in step 104 and will not be described in detail here.

After obtaining the data required for the calculation, the computing device may calculate a business risk score through a business risk model.

In one possible implementation, the business risk model includes a water line model that may calculate a first score indicative of the repayment capability of the subject to be evaluated based on the receivables and the amounts at credit of the subject to be evaluated.

The computing device may first obtain the present credit of the subject to be evaluated; and then acquiring the inventory value, the amount to be refunded, the return rate, the refund rate, the in-transit funds and the reserved amount from store operation data of all stores of the subject to be evaluated.

Then, the computing device may input the inventory value, the amount to be refund, the return rate, the refund rate, the in-transit funds, and the reserved amount into the water line model, and calculate an receivables amount through the water line model; inputting the on-credit into the water line model, and obtaining a first score based on the ratio of the receivables to the on-credit through the water line model; the business risk score is calculated based on the first score.

Where receivables = (inventory value + amount to be refunded) × (1-return rate) × refund rate + in-transit funds + reserved amount.

Specifically, the inventory value refers to the sum of the inventory values of all commodities with the current store ages within 0-180 days; the amount to be refund refers to the amount of the generated shipping order that has not yet been refunded; the in-transit amount refers to the amount that has been paid by Amazon but has not yet been credited by the cashier; the return rate refers to the ratio of the amount of the return order in the last year to the sales in the last year; the refund rate refers to the ratio of the refund amount in the last year to the sales amount in the last year.

The larger the ratio of the account to the credit amount, the stronger the compensation ability of the main body to be evaluated is; whereas the weaker. Illustratively, when the ratio of the amount to be charged to the amount to be credited is greater than 1.5, the water line model may determine that the risk of operation in the dimension of the compensation capability is low, thereby obtaining a corresponding first score 100; when the ratio of the amount to be charged is greater than 0.8, the water line model may determine that the risk of operation in the dimension of the compensation capability is high, resulting in a corresponding first score 60.

It will be appreciated that when the computing device evaluates the business risk solely through the water line model, the first score may be directly used as the business risk score; when the computing device comprehensively evaluates the business risk through a plurality of business risk models including the water line model, the computing device may calculate a business risk score based on the first score.

It will be appreciated that in the case where the computing device evaluates the risk of the business solely through the water line model, if the first score is low, which indicates that the repayment capability of the subject to be evaluated is limited, the computing device may directly perform step 108 and output corresponding early warning information.

Through a water line model, using a digital means to manage purchasing, inventory and distribution conditions of shops of a main body to be evaluated in a full-link mode, and calculating accounts receivable; and then, based on the accounts receivable and the credit amount, predicting the fund requirement and the compensation capability of the main body to be evaluated, so that the withdrawal amount of the main body to be evaluated can be controlled in an auxiliary manner, and real-time post-credit monitoring and early warning can be realized.

In one possible implementation, the business risk model comprises a cash flow stabilization model, and the store business data comprises a store daily sales amount; the computing device may input the store day sales into the cash flow stability model, calculate a sum of store day sales last week and an average of N store day sales lowest in the last year from the cash flow stability model; then, obtaining a second score based on the ratio of the sum of sales of the store days of the last week to the average value through the cash flow stabilization model; the business risk score is calculated based on the second score.

Wherein N is an integer greater than 1. Illustratively, N may be 12.

Alternatively, when the computing device evaluates the business risk solely by the cash flow stabilization model, the ratio of the sum of sales at the last week's store day to the average may be directly used as the business risk score, directly indicating the size of the business risk.

Illustratively, the cash flow stabilization model may determine that the business risk is low when the ratio of the sum of the last week's store day sales to the average is within the interval of 60 to 100; when the ratio is within the interval of 20 to 60, the cash flow stability model may determine that the business risk is in range; when the ratio is within the interval of 0 to 20, the cash flow stabilization model may determine that the risk of operation is high.

When the cash flow stabilization model is used in combination with other business risk models, the computing device may convert the risk level indicated by the ratio of the sum of sales at the store day of the last week to the average value into a second score under the unified standard of each business risk model, and calculate a business risk score based on the second score.

The cash flow stabilization model focuses on sales data of a store, and can determine that the store is in a specific stage of a life cycle (a new store period, a lifting period, a maturation period, a decay period and a degradation period) through the change of the sales data; by comparing the average value of the sales of the store in the nearest week with the average value of the sales of the store in the lower day, the store with high stability and high maintainability can be accurately evaluated and distinguished.

In another possible implementation, the business risk model comprises a warehouse clearance risk model, the store business data comprises a quantity and price of a single item, the single item comprising a warehouse clearance single item; the computing equipment can input the number and the price of the single products into the warehouse-clearing risk model, calculate the total value of the warehouse-clearing single products based on the number and the price of the warehouse-clearing single products through the warehouse-clearing risk model, and calculate the total value of all the single products based on the number and the price of all the single products; then, a third score is obtained based on the ratio of the total value of the warehouse-cleaning single product to the total value of all the single products through the warehouse-cleaning risk model; the business risk score is calculated based on the third score.

The warehouse clearing risk model judges whether a shop is in a warehouse clearing state or not by calculating the cargo value ratio of warehouse clearing single products; when the inventory value of the warehouse clearance single product is larger than a certain proportion, such as 30%, the warehouse clearance risk model can judge that the store is in a warehouse clearance state, and warehouse clearance risks exist.

Prior to calculation of the inventory risk model, the computing device needs to determine inventory items in the store. Optionally, the computing device determines that the item is a warehouse-cleared item if a proportion of used items for the item is greater than a first threshold and a discount off sales in the last three months is greater than a second threshold, the proportion of used items being a ratio of a number of the items to a total number of the items for a warehouse time greater than 180 days.

Illustratively, the first threshold is 90%.

Wherein the second threshold is an average discount off sales for the same or similar items over the same period of time. Illustratively, the second threshold is a 15% discount.

The warehouse clearance risk model can monitor discounts and inventory conditions of various single products of the store in real time through big data, and can accurately identify the business conditions and the warehouse clearance risks of the store by comparing average discount levels of similar products in the same time period.

It will be appreciated that the multiple business risk models described above may be used alone or in combination. Referring to fig. 2, fig. 2 is a data flow chart in a risk early warning process according to an embodiment of the present application.

As shown in fig. 2, the computing device pre-processes the store operation data to obtain a scale level, first derivative data and second derivative data; the scale level and the first derivative data are then input into a compliance risk model, and the scale level and the second derivative data are input into a water line model, a cash flow stabilization model, and a clearance risk model, respectively.

The computing device then calculates, via the compliance risk model, a compliance risk score based on the first derivative data using an evaluation criterion corresponding to the scale level.

Then, calculating to obtain a first score by using an evaluation standard corresponding to the scale level based on the second derivative data through a water line model; calculating to obtain a second score by using an evaluation standard corresponding to the scale level based on the second derivative data through the cash flow stability model; calculating to obtain a third score by adopting an evaluation standard corresponding to the scale level based on the second derivative data through the bin clearance risk model; and then carrying out weighted calculation on the first score, the second score and the third score to obtain the business risk score.

Finally, the computing device may execute step 108, outputting risk early warning information based on the compliance risk score and the business risk score.

Optionally, the computing device may sum the first score, the second score, and the third score to obtain the business risk score.

And step 108, the computing equipment outputs risk early warning information based on the compliance risk score and the business risk score.

After the compliance risk score and the business risk score are obtained, the computing device may output corresponding risk early warning information. Specifically, the computing device may output early warning information of the compliance risk and early warning information of the management risk, respectively; and the comprehensive risk score and the operation risk score can be synthesized, and after the comprehensive risk judgment is carried out on the main body to be evaluated, a corresponding evaluation early warning report is output.

The compliance risk score and the management risk score can perform early warning at a post-loan stage in the loan, and can reject loan application of the subject to be evaluated with higher compliance risk and management risk at a pre-loan stage. In particular, the compliance risk model and cash flow stabilization model above may be used to screen subjects to be evaluated.

Illustratively, the range of compliance risk scores is 0 to 1000 points, the higher the score the lower the risk; when the compliance risk score is within the interval of 0 to 100 minutes, the computing device can output early warning information of high risk; when the compliance risk score is within the interval of 100 to 200 minutes, the computing device can output early warning information of the middle risk; when the compliance risk score is within the interval of 200 to 1000 minutes, the computing device may output low risk pre-warning information. The financial institution can credit and approve the main body to be evaluated based on the risk early warning information.

The risk early-warning method in the embodiment of the present application is described above, and the risk early-warning device in the embodiment of the present application is described below, referring to fig. 3, an embodiment of the risk early-warning device 300 in the embodiment of the present application includes:

an acquiring module 301, configured to acquire store operation data of a subject to be evaluated;

a first evaluation module 302, configured to input the store operation data into a compliance risk model to obtain a compliance risk score;

a second evaluation module 303, configured to input the store operation data into an operation risk model, to obtain an operation risk score;

and the early warning module 304 is configured to output risk early warning information based on the compliance risk score and the business risk score.

In one possible implementation, the apparatus 300 further includes: a preprocessing module 305 for calculating a scale level of a store of the subject to be evaluated based on the store business data, and first derivative data and second derivative data, wherein the first derivative data is data required for the calculation of the compliance risk model, and the second derivative data is data required for the calculation of the business risk model; the first evaluation module 302 is specifically configured to input the first derivative data into the compliance risk model, calculate, based on the evaluation criteria corresponding to the scale level, through the compliance risk model, and obtain the compliance risk score; the second evaluation module 303 is specifically configured to input the second derivative data into the business risk model, calculate, based on the evaluation criteria corresponding to the scale level, through the business risk model, and obtain the business risk score.

In one possible implementation, the store operating data includes a platform score and sales of a secondary store, and sales of a primary store, the secondary store being a child of the primary store, wherein the platform score is a policy compliance score of an electronic commerce platform in which the secondary store resides for the secondary store; the first evaluation module 302 is specifically configured to input the platform score and sales of the secondary store and sales of the primary store into the compliance risk model, and calculate the compliance score corresponding to the primary store based on the platform score of the secondary store and a ratio of the sales of the secondary store to the sales of the primary store through the compliance risk model; and calculating the compliance risk score based on the compliance score and sales of the first store of the subject to be evaluated through the compliance risk model.

In one possible implementation, the business risk model comprises a water line model, and the store business data comprises inventory value, amount to be refunded, return rate, refund rate, in-transit funds, and reserved amount; the obtaining module 301 is further configured to obtain an on-credit amount of the subject to be evaluated; the second evaluation module 303 is specifically configured to input the inventory value, the amount to be refund, the return rate, the refund rate, the in-transit funds and the reserved amount into the water line model, and calculate an accounts receivable through the water line model; inputting the on-credit into the water line model, and obtaining a first score based on the proportion of the receivables and the on-credit through the water line model; the business risk score is calculated based on the first score.

In one possible implementation, the business risk model comprises a cash flow stabilization model, and the store business data comprises a store daily sales amount; the second evaluation module 303 is specifically configured to input the sales of the store day into the cash flow stability model, calculate an average value of the sales of the lowest N store days in the last year and a sum of sales of the store days in the last week through the cash flow stability model, where N is an integer greater than 1; obtaining a second score based on a ratio of a sum of sales of store days of the last week to the average value by the cash flow stabilization model; the business risk score is calculated based on the second score.

In one possible implementation, the business risk model comprises a warehouse clearance risk model, the store business data comprises a quantity and price of the individual items, the individual items comprising warehouse clearance individual items; the second evaluation module 303 is specifically configured to input the number and price of the single products into the warehouse-clearing risk model, calculate the total value of the warehouse-clearing single products based on the number and price of the warehouse-clearing single products through the warehouse-clearing risk model, and calculate the total value of all the single products based on the number and price of all the single products; obtaining a third score based on the ratio of the total value of the warehouse-removed individual items to the total value of all individual items through the warehouse-removed risk model; the business risk score is calculated based on the third score.

In one possible implementation, the second evaluation module 303 is specifically configured to determine that the item is a warehouse-free item if a proportion of the item used is greater than a first threshold and a discount off sales in the last three months is less than a second threshold, the proportion of the used being a ratio of the number of items greater than 180 days in the warehouse to the total number of items.

The risk early-warning device 300 provided in the embodiment of the present application may be understood by referring to the corresponding content of the foregoing risk early-warning method embodiment, and the detailed description is not repeated here.

In other possible embodiments, the present application further provides a computing device, and in particular, reference may be made to fig. 4, where fig. 4 is a schematic structural diagram of the computing device according to an embodiment of the present application. As shown in fig. 4, a computing device 400 provided by an embodiment of the present application includes a processor 410 and a memory 420.

Wherein processor 410 may include one or more processing cores. The processor 410 utilizes various interfaces and lines to connect various portions of the computing device 400, by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 420, and invoking data stored in the memory 420, to perform the methods provided by any one or more of the embodiments described above. Alternatively, the processor 410 may be implemented in at least one hardware form of Digital Signal Processing (DSP), field-programmable gate array (FPGA), programmable logic array (programmable logic array, PLA). The processor 410 may integrate one or a combination of a CPU, an image processor (graphics processing unit, GPU) and a modem. It will be appreciated that the modem may not be integrated into the processor 410 and may be implemented solely by a single communication chip.

The memory 420 may include a random access memory (random access memory, RAM) or a read-only memory (ROM). Optionally, memory 420 includes a non-transitory computer readable medium (non-transitory computer-readable storage medium). Memory 420 may be used to store instructions, programs, code sets, or instruction sets. Memory 420 may include a memory program area. The storage program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing a method of an embodiment of the present application, and so on.

Wherein processor 410 and memory 420 are communicatively coupled via a bus within computing device 400, which may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus, or an extended industry standard architecture (extended industry standard architecture, EISA) bus, or the like. The bus may be classified as an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in fig. 4, but not only one bus or one type of bus.

In another embodiment of the present application, there is also provided a computer-readable storage medium having stored therein computer-executable instructions that, when executed by at least one processor of a device, perform the method flow described in any of the embodiments of fig. 1 or fig. 2 above.

In another embodiment of the present application, there is also provided a computer program product comprising computer-executable instructions stored in a computer-readable storage medium; the at least one processor of the device may read the computer-executable instructions from the computer-readable storage medium, and execution of the computer-executable instructions by the at least one processor causes the device to perform the method flow described above in any of the embodiments of fig. 1 or 2.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the embodiments of the present application.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.

In the embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the embodiments of the present application may be embodied in essence or a part contributing to the prior art or a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

Claims

1. A risk early warning method, which is characterized by being applied to a computing device; the method comprises the following steps:

acquiring store operation data of a subject to be evaluated;

inputting the store operation data into a compliance risk model to obtain a compliance risk score;

Inputting the store business data into a business risk model to obtain a business risk score;

And outputting risk early warning information based on the compliance risk score and the business risk score.

2. The method of claim 1, wherein after the acquiring store business data of the subject under evaluation, the method further comprises:

Calculating a scale level of a store of the subject to be evaluated based on the store business data, and first derivative data and second derivative data, wherein the first derivative data is data required for the calculation of the compliance risk model, and the second derivative data is data required for the calculation of the business risk model;

inputting the store operation data into a compliance risk model to obtain a compliance risk score, including:

Inputting the first derivative data and the scale level into the compliance risk model, and calculating based on the evaluation standard corresponding to the scale level through the compliance risk model to obtain the compliance risk score;

inputting the store business data into a business risk model to obtain a business risk score, including:

And inputting the second derivative data and the scale level into the operation risk model, and calculating based on the evaluation standard corresponding to the scale level through the operation risk model to obtain the operation risk score.

3. The method of claim 1 or 2, wherein the store operating data comprises a platform score and sales of a secondary store, and sales of a primary store, the secondary store being a child of the primary store, wherein the platform score is a policy compliance score of the secondary store by an electronic commerce platform in which the secondary store is located; inputting the store operation data into a compliance risk model to obtain a compliance risk score, including:

Inputting the platform score and sales of the secondary store and sales of the primary store into the compliance risk model, and calculating the compliance score corresponding to the primary store based on the platform score of the secondary store and the ratio of the sales of the secondary store to the sales of the primary store through the compliance risk model;

And calculating the compliance risk score based on the compliance score and sales of the first store of the subject to be evaluated through the compliance risk model.

4. The method of claim 1 or 2, wherein the business risk model comprises a water line model, and the store business data comprises inventory value, amount to be refunded, return rate, refund rate, in-transit funds, and reserved amount; before the store business data is input into the business risk model to obtain the business risk score, the method further comprises:

acquiring the on-credit amount of the main body to be evaluated;

Inputting the inventory value, the amount to be refund, the return rate, the refund rate, the on-transit funds and the reserved amount into the water line model, and calculating to obtain accounts receivable through the water line model;

Inputting the on-credit amount into the water line model, and obtaining a first score through the water line model based on the ratio of the accounts receivable to the on-credit amount;

and calculating the operation risk score based on the first score.

5. The method of claim 1 or 2, wherein the business risk model comprises a cash flow stabilization model and the store business data comprises a store day sales; inputting the store business data into a business risk model to obtain a business risk score, including:

Inputting the sales of the shops into the cash flow stabilizing model, calculating the sum of sales of the shops in the last week and the average value of the sales of the shops in the lowest N shops in the last year through the cash flow stabilizing model, wherein N is an integer larger than 1;

obtaining a second score based on a ratio of a sum of sales of store days of the last week to the average value by the cash flow stabilization model;

And calculating the operation risk score based on the second score.

6. The method of claim 1 or 2, wherein the business risk model comprises a warehouse clearance risk model, the store business data comprises a quantity and price of individual items, the individual items comprise warehouse clearance individual items; inputting the store business data into a business risk model to obtain a business risk score, including:

Inputting the quantity and the price of the single products into the warehouse-clearing risk model, calculating the total value of the warehouse-clearing single products based on the quantity and the price of the warehouse-clearing single products through the warehouse-clearing risk model, and calculating the total value of all the single products based on the quantity and the price of all the single products;

Obtaining a third score based on the ratio of the total value of the warehouse-removed single products to the total value of all the single products through the warehouse-removed risk model;

and calculating the operation risk score based on the third score.

7. The method of claim 6, wherein prior to said entering the store business data into a business risk model to derive a business risk score, the method further comprises:

and if the old goods proportion of the single products is larger than a first threshold value and the sale discount in the last three months is larger than a second threshold value, determining that the single products are warehouse-removed single products, wherein the old goods proportion is the ratio of the number of the single products to the total number of the single products in a warehouse time of more than 180 days.

8. A risk early warning device, the device comprising:

the acquisition module is used for acquiring store operation data of the main body to be evaluated;

The first evaluation module is used for inputting the store operation data into a compliance risk model to obtain a compliance risk score;

the second evaluation module is used for inputting the store management data into a management risk model to obtain a management risk score;

And the early warning module is used for outputting risk early warning information based on the compliance risk score and the management risk score.

9. A computing device, the computing device comprising a memory and a processor;

The memory is coupled to the processor;

the memory is used for storing computer program instructions;

The processor is configured to invoke the computer program instructions to perform the method of any of claims 1-7.

10. A computer-readable storage medium comprising, the computer-readable storage medium has stored therein computer-executable instructions; wherein the computer-executable instructions, when executed by a processor, implement the method of any of claims 1-7.