Enterprise financial risk management system and method based on big data

Abstract

The invention provides an enterprise financial risk management system and method based on big data, and relates to the technical field of enterprise financial risk management.The method comprises the steps that account information data of a to-be-managed enterprise is obtained, an account evaluation period is calculated, and the money and period ratio of a customer is calculated according to the account data of each customer every time; the clients are grouped through a clustering method, the groups are sorted by calculating the payment period ratio expected value of each group, the account amount distribution of each group is calculated, the account structure safety coefficient is calculated, the credibility and the repayment rate of the clients in each account evaluation period are calculated, and the risk coefficient of the clients is calculated; and calculating an account evaluation index according to the account structure safety coefficient and the customer risk coefficient, updating the account data at the end moment of the account evaluation cycle, recalculating the account evaluation index in the new cycle, and calculating the account risk coefficient according to the change of the account evaluation index.

Description

Technical Field

[0001] The present invention relates to the technical field of enterprise financial risk management, and in particular to an enterprise financial risk management system and method based on big data. Background Art

[0002] Accounts receivable is an important part of the current assets of an enterprise, and its management efficiency directly affects the cash flow and financial health of the enterprise. Effective accounts receivable management can help enterprises reduce bad debt losses, improve the efficiency of capital use, and optimize credit policies. With the continuous expansion of the scale of modern enterprises and the increasingly complex operating environment, enterprises are facing more and more financial risks in their daily operations, especially the management of accounts receivable. Traditional financial risk management methods usually rely on manual experience or simple historical data analysis, lacking dynamic monitoring of corporate accounts receivable and detailed risk assessment. This leads to problems such as delayed response and inaccurate prediction when enterprises deal with potential financial risks, especially in terms of customer credit assessment, account structure analysis and risk warning. In addition, traditional methods are difficult to comprehensively consider the multi-dimensional information of accounts receivable, such as account amount, collection cycle, customer credibility and other factors, and thus cannot effectively identify and predict account risks.

[0003] In order to deal with this problem, more and more companies are beginning to explore intelligent financial risk management systems based on big data analysis, extracting more accurate risk characteristics through comprehensive analysis of accounts receivable data, thereby achieving real-time monitoring and early warning of accounts receivable risks. However, while existing technologies comprehensively consider customer accounts receivable behavior and creditworthiness, they lack a complete enterprise financial risk assessment system based on data models, and are unable to accurately quantify and dynamically track the changing trends of accounts receivable risks, limiting the effectiveness and accuracy of enterprise financial risk management.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The purpose of the present invention is to provide an enterprise financial risk management system and method based on big data to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions: An enterprise financial risk management system based on big data, comprising: A data collection module, which is used to obtain the account information data of the enterprise to be managed, and calculate the average collection period of each historical account as the account evaluation period; A customer grouping module, which is used to calculate the customer's payment period ratio according to the account amount, account generation time and account due time of each customer's account data, and group the customers by clustering method based on the average value of the customer's payment period ratio; An account receivable analysis module, which is used to sort the clustered groups according to the result of customer clustering by calculating the expected value of the payment period ratio of each group, and calculate the account receivable amount distribution of each group and the account receivable structure safety factor according to the sorting order of each group; A customer analysis module, which is used to calculate the customer's creditworthiness based on the account generation time, account due time, and account collection time of each account in each account assessment cycle of each customer, calculate the repayment rate based on the account amount and repayment amount in the cycle, and calculate the customer risk coefficient based on the creditworthiness in each cycle and the repayment rate in the cycle; An assessment and early warning module is used to calculate an accounts receivable assessment index based on the accounts receivable structure safety factor and the customer risk factor, update the accounts receivable data at the end of the accounts receivable assessment cycle, recalculate the accounts receivable assessment index in the new cycle, and calculate the accounts receivable risk factor based on changes in the accounts receivable assessment index.

[0007] Furthermore, the receivables data includes customer name, number of receivables, receivables amount, receivables generation time, receivables due time, receivables collection time, and receivables amount; The calculation method of the accounts receivable assessment period is: in, is the accounts receivable assessment cycle, For the The time when the account was generated. For the The payment time of the next account, is the amount of accounts receivable, Is a positive integer.

[0008] Furthermore, the specific calculation formula for calculating the average payment period ratio of the customer is: in, The payment period ratio for customers, For customers The payment period ratio of the account, is the average payment period ratio of customers, is the customer's account amount, The time when the account is due, The time when the account was generated. The amount of accounts payable for each customer, Is a positive integer.

[0009] Furthermore, the method of grouping customers by clustering is: The average payment period ratio of each customer is taken as a data node, and randomly selected data nodes as the initial centroid, represents the number of categories after clustering, is a positive integer, where The initial centroid is expressed as: , Indicates The average payment period ratio of the customers with the data nodes as the initial centroid, is a positive integer, and ; The average payment-to-period ratio of customers is taken as the node feature vector. For the feature vector in each region, its distance to each initial centroid is calculated and assigned to the cluster represented by the nearest centroid. The formula for calculating the distance to the initial centroid is: in, Indicates The initial centroid and The distance between data nodes, Indicates The average payment period ratio of customers corresponding to each data node; For each cluster, after each clustering is completed, the mean of all points in the cluster is recalculated and used as the feature data of the new centroid. The update formula of the centroid feature data is: in, Indicates that the The number of data nodes of the centroid, Indicates that the The average payment period ratio of the customers corresponding to the data nodes of the centroid, represents the mean of the payment-period ratio of the updated centroid; Based on the updated feature vector of the centroid, clustering is performed again until the change of all centroid positions is less than the threshold, then the clustering is considered stable and the clustering is terminated.

[0010] Furthermore, the calculation formula for calculating the expected value of the payment-period ratio of each group is: in, is the expected value of the payment period ratio for each group, For each group The average payment period ratio of each customer, is the number of customers in each group, is a positive integer; According to the numerical value of the expected value of the payment period ratio of each group, the groups are sorted in descending order.

[0011] Furthermore, the calculation formula for the distribution of the amount of accounts receivable of each group is: in, For each group, the amount of accounts receivable is distributed. For each group The amount of the account of each customer; The calculation formula of the safety factor of the accounts receivable structure is: in, is the safety factor of the accounts receivable structure, is the number of groups after grouping, After sorting The distribution of accounts receivable amount in each group.

[0012] Furthermore, the calculation formula of the customer's reputation is: in, For the credibility of customers, The time when the account is due, The time when the account was generated. The payment collection time. The first Accounts, The number of accounts receivable during the customer account assessment period; The calculation formula of the repayment rate is: in, The repayment rate for the customer, The amount of the customer's accounts receivable during the accounts receivable assessment period. The repayment amount of the customer during the account assessment period; The formula for calculating the customer risk factor based on the credit rating and repayment rate in each cycle is: in, The customer risk factor.

[0013] Furthermore, the calculation formula for calculating the account evaluation index based on the account structure safety factor and the customer risk factor is: in, is the accounts receivable valuation index, is the customer risk factor, is the safety factor of the accounts receivable structure, are the weights of customer risk factor and account structure safety factor, respectively. , .

[0014] Furthermore, the step of updating the accounts receivable data at the end of the accounts receivable evaluation cycle is as follows: First, you need to determine the current account receivable balance for each customer. Based on the account generation time, use the first-in-first-out method to offset the account amount with the repayment amount in the order of account generation time from earliest to latest. The formula for calculating the accounts receivable risk coefficient based on the change in the accounts receivable evaluation index is: in, is the mean value of the accounts receivable valuation index, is the fluctuation value of the accounts receivable valuation index, is the account risk factor, For the The accounts receivable evaluation index within an accounts receivable evaluation cycle, The number of cycles for the receivables assessment; when If the risk is judged to be high, debt collection measures should be taken immediately; in, The threshold for assessing accounts receivable risk.

[0015] The present invention further provides a method for enterprise financial risk management based on big data, wherein the enterprise financial risk management is performed by the above-mentioned enterprise financial risk management system based on big data, and the specific steps include: Step 1: Obtain the account information data of the enterprise to be managed, and calculate the average collection period of each historical account as the account evaluation period; Step 2: Calculate the customer's payment period ratio based on the account amount, account generation time and account repayment time of each customer's account data. Use the average of the customer's payment period ratio as a feature and group the customers by clustering method. Step 3: Based on the results of customer clustering, sort the clustered groups by calculating the expected value of the payment period ratio of each group, calculate the distribution of the account amount of each group, and calculate the account structure safety factor based on the sorting order of each group; Step 4: Calculate the customer's creditworthiness based on the account generation time, account repayment time, and account collection time of each account in each account assessment cycle of each customer; calculate the repayment rate based on the account amount and repayment amount in the cycle; and calculate the customer risk factor based on the creditworthiness and repayment rate in each cycle; Step 5: Calculate the accounts receivable assessment index based on the accounts receivable structure safety factor and the customer risk factor. Update the accounts receivable data at the end of the accounts receivable assessment cycle, recalculate the accounts receivable assessment index in the new cycle, and calculate the accounts receivable risk factor based on the changes in the accounts receivable assessment index.

[0016] Compared with the prior art, the present invention has the following beneficial effects: Obtain the accounts receivable information data of the enterprise to be managed, calculate the accounts receivable evaluation cycle, calculate the customer's payment period ratio based on each customer's accounts receivable data, group the customers by clustering method, sort the groups by calculating the expected value of the payment period ratio of each group, calculate the accounts receivable structure safety factor by calculating the accounts receivable amount distribution of each group, calculate the customer risk factor by calculating the customer's creditworthiness and repayment rate in each accounts receivable evaluation cycle, calculate the accounts receivable evaluation index based on the accounts receivable structure safety factor and the customer risk factor, update the accounts receivable data at the end of the accounts receivable evaluation cycle, recalculate the accounts receivable evaluation index in the new cycle, and calculate the accounts receivable risk factor based on the change in the accounts receivable evaluation index; The present invention is based on big data technology, comprehensively considers various key data of accounts receivable, and uses cluster analysis to group customers, which can accurately identify the financial risk characteristics of different customer groups. The system can dynamically calculate the accounts receivable assessment index and accounts receivable risk coefficient based on the big data analysis results, so that enterprises can monitor accounts receivable risks in real time and predict future financial conditions. By combining the accounts receivable structure safety factor with the customer risk factor, enterprises can comprehensively and accurately evaluate the security of accounts receivable and provide data support for financial decision-making; The present invention can also help enterprises identify potential risk changes in advance through periodic data updates and dynamic assessments, and take timely countermeasures, thereby optimizing capital flows, improving the financial health of the enterprise, and enabling the enterprise to maintain a higher risk prevention capability in a complex and changing economic environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the overall system structure of the present invention; Figure 2 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION

[0018] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0019] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0020] Example

[0021] See also Figure 1 , the present invention provides a technical solution: An enterprise financial risk management system based on big data includes a data collection module, a customer grouping module, an account analysis module, a customer analysis module and an evaluation and early warning module, wherein: The data collection module is used to obtain the account information data of the enterprise to be managed, and calculates the average collection period of each historical account as the account evaluation period.

[0022] By calculating the average collection period based on the actual data of historical accounts receivable, the actual account collection situation of the enterprise can be more accurately reflected. Compared with traditional simple assumptions or estimates, this data-based analysis method can significantly improve the accuracy of financial forecasts and the reliability of risk assessment.

[0023] Traditional accounts receivable management may rely on empirical judgment or a unified collection cycle, but the average collection cycle calculated through data as the accounts receivable assessment cycle can provide a quantitative basis for each company, helping financial personnel make more informed decisions and avoid over-reliance on manual speculation. Historical data can be continuously updated, and companies can dynamically adjust their accounts receivable management strategies based on new accounts receivable situations. This feature enables companies to respond more flexibly to market and customer changes, rather than sticking to an unchanging management method. By providing real accounts receivable cycle data, it can provide a more accurate basis for risk assessment, allowing the overall system to more effectively identify risk points and avoid misjudgments.

[0024] At the same time, the receivables assessment cycle allows financial personnel to formulate more scientific receivables management strategies based on historical data. For example, in subsequent risk assessments and customer credit calculations, the real data of historical collection cycles can help identify potential financial risks and optimize the company's capital turnover and management.

[0025] In this embodiment, the account data includes customer name, account quantity, account amount, account generation time, account repayment time, account collection time, and repayment amount.

[0026] The calculation method of the accounts receivable assessment period is: in, is the accounts receivable assessment cycle, For the The time when the account was generated. For the The payment time of the next account, is the amount of accounts receivable, Is a positive integer.

[0027] The customer grouping module is used to calculate the customer's payment period ratio based on the account amount, account generation time and account due time of each customer's account data, and group the customers by clustering method based on the average value of the customer's payment period ratio.

[0028] By calculating the customer's payment period ratio, we can accurately quantify the customer's account collection cycle, the relationship between the account amount and the collection time, and further reflect the customer's payment habits and repayment ability. This quantitative method makes the assessment of customer credit more accurate. Traditional customer grouping methods may rely on manual experience or simple account period division, while this step automatically groups customers through clustering algorithms, which can form personalized grouping results based on each customer's historical behavioral characteristics. These groups can better reflect the financial risk levels of different customers.

[0029] The introduction of clustering method can identify the heterogeneity between different groups, ensuring that customer groups with different account collection cycles and repayment behaviors can be found. For the risk characteristics of each customer group, the enterprise can adopt different management strategies.

[0030] The results of customer grouping will provide core data support for the subsequent sorting of expected payment period ratios, calculation of account structure safety factors and customer risk factors. By grouping customers, appropriate risk management strategies can be formulated based on the characteristics of different customer groups.

[0031] Through cluster analysis, enterprises can adopt differentiated financial management strategies for different customer groups. For example, they can strengthen collection efforts for high-risk customer groups, and extend the payment period or provide more flexible payment methods for low-risk customer groups, thereby achieving personalized customer management and improving overall capital recovery efficiency.

[0032] In this embodiment, the specific calculation formula for calculating the average payment period ratio of the customer is: in, The payment period ratio for customers, For customers The payment period ratio of the account, is the average payment period ratio of customers, is the customer's account amount, The time when the account is due, The time when the account was generated. The amount of accounts payable for each customer, Is a positive integer.

[0033] In this embodiment, the method of grouping customers by clustering is: The average payment period ratio of each customer is taken as a data node, and randomly selected data nodes as the initial centroid, represents the number of categories after clustering, is a positive integer, where The initial centroid is expressed as: , Indicates The average payment period ratio of the customers with the data nodes as the initial centroid, is a positive integer, and ; The average payment-to-period ratio of customers is taken as the node feature vector. For the feature vector in each region, its distance to each initial centroid is calculated and assigned to the cluster represented by the nearest centroid. The formula for calculating the distance to the initial centroid is: in, Indicates The initial centroid and The distance between data nodes, Indicates The average payment period ratio of customers corresponding to each data node; For each cluster, after each clustering is completed, the mean of all points in the cluster is recalculated and used as the feature data of the new centroid. The update formula of the centroid feature data is: in, Indicates that the The number of data nodes of the centroid, Indicates that the The average payment period ratio of the customers corresponding to the data nodes of the centroid, represents the mean of the payment-period ratio of the updated centroid; Based on the updated feature vector of the centroid, clustering is performed again until the change of all centroid positions is less than the threshold, then the clustering is considered stable and the clustering is terminated.

[0034] The receivables analysis module is used to sort the clustered groups according to the results of customer clustering by calculating the expected value of the payment period ratio of each group, and to calculate the receivables structure safety factor by calculating the receivables amount distribution of each group and according to the sorting order of each group.

[0035] By analyzing the distribution of the amount of accounts receivable of each customer group and sorting the results, it is possible to accurately determine which customer groups have higher risks. In particular, when the accounts receivable structure is concentrated in groups with larger grouping numbers, it indicates that the amount of money collected per unit time is large, but the difficulty of collecting money is also high, indicating that the company's accounts receivable distribution risk is high. This situation can be identified early and targeted management can be carried out. By analyzing the changes in the expected value of the payment period ratio and the distribution of the amount of accounts receivable of customer groups in real time, the financial health of the company can be dynamically monitored. When the accounts receivable structure tends to be unsafe or it is difficult to collect money, the system can quickly identify and feedback to the management, so that timely risk control measures can be taken.

[0036] The big data analysis method is used to cluster, sort and analyze customer groups. By calculating the expected value of the account amount distribution and the payment period ratio, the account structure of the customer group can be revealed more systematically, avoiding relying solely on traditional account periods or credit assessments. This structured analysis method is more accurate and can provide a more reliable basis for financial decision-making. Once it is found that the account structure is too concentrated and the risk of difficulty in collecting payments is high, the system will issue an early warning in time to help the company identify financial risks in advance and avoid capital chain breaks or bad debts. It also enables the company to fully understand the overall financial situation. The implementation of this step provides a more detailed analysis framework for financial risk management, making the company more scientific and accurate in the overall financial health assessment, thereby improving the company's ability to resist risks in a complex environment.

[0037] In this embodiment, the calculation formula for calculating the expected value of the payment period ratio of each group is: in, is the expected value of the payment period ratio for each group, For each group The average payment period ratio of each customer, is the number of customers in each group, is a positive integer; According to the numerical value of the expected value of the payment period ratio of each group, the groups are sorted in descending order.

[0038] In this embodiment, the calculation formula for the distribution of the amount of accounts receivable of each group is: in, For each group, the amount of accounts receivable is distributed. For each group The amount of the account of each customer; The calculation formula of the safety factor of the accounts receivable structure is: in, is the safety factor of the accounts receivable structure, is the number of groups after grouping, After sorting The distribution of accounts receivable amount in each group.

[0039] The customer analysis module is used to calculate the customer's credibility based on the account generation time, account repayment time, and account collection time of each account in each account assessment cycle of each customer, calculate the repayment rate based on the account amount and repayment amount in the cycle, and calculate the customer risk coefficient based on the credibility in each cycle and the repayment rate in the cycle.

[0040] By comprehensively considering factors such as the time when accounts are generated, the time when they are due, and the time when they are collected, the creditworthiness of customers can be comprehensively assessed. By calculating the repayment rate for each cycle, the repayment behavior and solvency of customers can be more objectively and accurately reflected, thus providing financial managers with a more accurate customer risk factor.

[0041] Traditional customer credit assessments are mostly based on static information, such as the customer's historical credit record and financial status, while this step can reflect the customer's credit status and repayment ability in real time by evaluating the dynamic data of each account cycle. In this way, companies can adjust credit policies and risk management strategies based on the actual situation of each account cycle.

[0042] Simply relying on the due date or amount of accounts receivable to assess risk can easily overlook the customer's repayment behavior, especially the timeliness of repayment. By calculating the collection time and repayment rate of accounts receivable, these behaviors are taken into consideration, making customer risk assessment more detailed and comprehensive. By quantifying the customer's creditworthiness and risk factor, companies can issue timely alarms when credit risk trends emerge, thereby taking effective collection measures or adjusting risk control strategies to prevent large-scale bad debts.

[0043] The credit status of a customer is a dynamic process that fluctuates over time, economic conditions, business changes, etc. By calculating the risk factor based on the creditworthiness of each account cycle, the trend of customer credit changes can be captured in real time.

[0044] The creditworthiness and repayment rate of each account cycle can reflect the customer's true credit status in a specific period of time. This cycle-based data reflects the customer's recent repayment behavior, so that customers who may have financial problems can be identified in a timely manner, rather than relying on the customer's past long-term record.

[0045] The time when accounts receivable are generated, the time when they are due, and the time when they are collected directly affect the customer's repayment ability. If the customer's account receivables are often delayed, it means that the customer has cash flow problems. By combining these time factors with the customer's repayment amount and repayment rate to evaluate the customer's creditworthiness, the customer's risk can be assessed more comprehensively.

[0046] Through periodic risk assessment, we can accurately measure the repayment performance of customers in different time periods, avoiding misjudgment caused by assessment at a single time point. For example, a customer may have performed well in the past, but recently failed to repay the account in time, which may cause its risk factor to increase, reflecting the risk potential of the customer in a timely manner.

[0047] In this embodiment, the calculation formula of the customer's reputation is: in, For the credibility of customers, The time when the account is due, The time when the account was generated. The payment collection time. The first Accounts, The number of accounts receivable during the customer account assessment period; The calculation formula of the repayment rate is: in, The repayment rate for the customer, The amount of the customer's accounts receivable during the accounts receivable assessment period. The repayment amount of the customer during the account assessment period; The formula for calculating the customer risk factor based on the credit rating and repayment rate in each cycle is: in, The customer risk factor.

[0048] Creditworthiness is an indicator that measures the integrity and reliability of a customer in fulfilling its repayment obligations within a specific account cycle. It is calculated based on the customer's account generation time, due time, and collection time within each cycle, reflecting the customer's performance in fulfilling its obligations on time within this cycle. The repayment rate refers to the ratio of the amount actually repaid by the customer to the amount due within the account assessment cycle. It directly reflects the customer's repayment ability and actual repayment situation. If the amount repaid by the customer is close to the amount due, the repayment rate is high, indicating that the customer has a strong repayment ability. If the customer only repays part of the account or fails to repay on time, the repayment rate is low, indicating that the customer has difficulty repaying the debt. The repayment rate within the cycle provides quantitative data on the customer's actual fulfillment of repayment obligations, helping companies to judge the customer's financial health and debt repayment ability. If the repayment rate is low, it may indicate that the customer's capital liquidity is insufficient and there is a greater risk.

[0049] The customer risk factor is an indicator that comprehensively considers the customer's creditworthiness and repayment rate in each billing cycle and is used to quantify the customer's financial risk level.

[0050] The assessment and early warning module is used to calculate the accounts receivable assessment index based on the accounts receivable structure safety factor and the customer risk factor, by updating the accounts receivable data at the end of the accounts receivable assessment cycle, recalculating the accounts receivable assessment index in the new cycle, and calculating the accounts receivable risk factor based on changes in the accounts receivable assessment index.

[0051] At the end of each receivables assessment cycle, the system will update the receivables assessment index based on new data (such as the customer's repayment status, receivables structure, etc.), which can accurately reflect the risk level of the current receivables and avoid lagging or outdated risk assessments. By combining the receivables structure safety factor and the customer risk factor, a more comprehensive receivables assessment index is calculated, which makes the risk assessment more comprehensive and accurate. The receivables structure safety factor mainly reflects the risk level of the receivables themselves, while the customer risk factor takes into account the customer's repayment ability and credit status. Through the comprehensive analysis of these two dimensions, the future risks of receivables can be predicted more accurately. For example, if the receivables structure safety factor is very low, but the customer risk factor is high, the system can remind the company that the receivables are at a high risk and require more stringent collection and follow-up measures.

[0052] In this embodiment, the calculation formula for calculating the account evaluation index based on the account structure safety factor and the customer risk factor is: in, is the accounts receivable valuation index, is the customer risk factor, is the safety factor of the accounts receivable structure, are the weights of customer risk factor and account structure safety factor, respectively. , .

[0053] In this embodiment, the step of updating the accounts receivable data at the end of the accounts receivable evaluation cycle is as follows: First, you need to determine the accounts receivable balance corresponding to each customer on the current date. According to the account generation time, use the first-in-first-out method and use the repayment amount to offset the account amount in the order of account generation time from the earliest to the latest.

[0054] The FIFO method is a common inventory management and cost accounting method. Its core concept is "the first purchased materials are sold or used first", that is, the first items to enter the inventory are used or sold first. In accounts receivable management, the FIFO principle means that the earliest accounts receivable will be settled or collected first. Through the FIFO method, companies can know more clearly which accounts receivable should be collected first. Since the earliest accounts receivable should be settled first according to the FIFO principle, when the age of the accounts exceeds a certain period of time, the company may give priority to the earliest accounts receivable rather than the recent ones. Suppose the company has two customers, one customer's accounts receivable was generated within one year, and the other customer's accounts receivable was generated two years ago. After the FIFO method is applied, the accounts receivable two years ago will be given priority for settlement or collection. This can avoid the backlog of overdue accounts and improve cash flow management. Compared with the average method or the last-in-first-out method, the FIFO method can more truly reflect the actual account recovery of the company and make the aging grouping more reasonable. When the company collects payment, the oldest accounts receivable are written off first, making the aging analysis more in line with the company's financial management logic and avoiding the aging classification of old accounts receivable being erroneously affected by the collection of new accounts receivable.

[0055] The formula for calculating the accounts receivable risk coefficient based on the change in the accounts receivable evaluation index is: in, is the mean value of the accounts receivable valuation index, is the fluctuation value of the accounts receivable valuation index, is the account risk factor, For the The accounts receivable evaluation index within an accounts receivable evaluation cycle, The number of cycles for the receivables assessment; when If the risk is judged to be high, debt collection measures should be taken immediately; in, The threshold for assessing accounts receivable risk.

[0056] The update of the receivables assessment cycle can help the system reflect the risk changes of receivables in real time. If the receivables data is not updated regularly, it will be difficult for the enterprise to detect the changes in the customer's credit status and receivables structure in time, and thus may miss potential financial risks. Therefore, periodically updating the receivables data and recalculating the receivables assessment index can provide real-time and dynamic risk warnings.

[0057] The receivables assessment index can more comprehensively and accurately reflect the risk level of receivables by considering the receivables structure safety factor and the customer risk factor. The receivables structure safety factor represents the health of the receivables, such as the repayment period and repayment method of the receivables; the customer risk factor assesses the customer's credit status and repayment ability. The receivables assessment index calculated by combining these two factors can provide a comprehensive risk warning information for the enterprise.

[0058] See also Figure 2 The present invention also provides a method for enterprise financial risk management based on big data, which is obtained by executing the above-mentioned enterprise financial risk management system based on big data, and the specific steps include: Step 1: Obtain the account information data of the enterprise to be managed, and calculate the average collection period of each historical account as the account evaluation period; Step 2: Calculate the customer's payment period ratio based on the account amount, account generation time and account repayment time of each customer's account data. Use the average of the customer's payment period ratio as a feature and group the customers by clustering method. Step 3: Based on the results of customer clustering, sort the clustered groups by calculating the expected value of the payment period ratio of each group, calculate the distribution of the account amount of each group, and calculate the account structure safety factor based on the sorting order of each group; Step 4: Calculate the customer's creditworthiness based on the account generation time, account repayment time, and account collection time of each account in each account assessment cycle of each customer; calculate the repayment rate based on the account amount and repayment amount in the cycle; and calculate the customer risk factor based on the creditworthiness and repayment rate in each cycle; Step 5: Calculate the accounts receivable assessment index based on the accounts receivable structure safety factor and the customer risk factor. Update the accounts receivable data at the end of the accounts receivable assessment cycle, recalculate the accounts receivable assessment index in the new cycle, and calculate the accounts receivable risk factor based on the changes in the accounts receivable assessment index.

[0059] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0060] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0061] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple 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.

[0062] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. An enterprise financial risk management system based on big data, characterized in that: include: A data collection module, which is used to obtain the account information data of the enterprise to be managed, and calculate the average collection period of each historical account as the account evaluation period; A customer grouping module, which is used to calculate the customer's payment period ratio according to the account amount, account generation time and account due time of each customer's account data, and group the customers by clustering method based on the average value of the customer's payment period ratio; An account receivable analysis module, which is used to sort the clustered groups according to the result of customer clustering by calculating the expected value of the payment period ratio of each group, and calculate the account receivable amount distribution of each group and the account receivable structure safety factor according to the sorting order of each group; A customer analysis module, which is used to calculate the customer's creditworthiness based on the account generation time, account due time, and account collection time of each account in each account assessment cycle of each customer, calculate the repayment rate based on the account amount and repayment amount in the cycle, and calculate the customer risk coefficient based on the creditworthiness in each cycle and the repayment rate in the cycle; An assessment and early warning module is used to calculate an accounts receivable assessment index based on the accounts receivable structure safety factor and the customer risk factor, update the accounts receivable data at the end of the accounts receivable assessment cycle, recalculate the accounts receivable assessment index in the new cycle, and calculate the accounts receivable risk factor based on changes in the accounts receivable assessment index.

2. The enterprise financial risk management system based on big data according to claim 1 is characterized by: The receivables data includes customer name, number of receivables, receivable amount, receivable generation time, receivable repayment time, receivable collection time, and repayment amount; The calculation method of the accounts receivable assessment period is: in, is the accounts receivable assessment cycle, For the The time when the account was generated. For the The payment time of the next account, is the amount of accounts receivable, Is a positive integer.

3. The enterprise financial risk management system based on big data according to claim 1 is characterized by: The specific calculation formula for calculating the average payment period ratio of the customer is: in, The payment period ratio for customers, For customers The payment period ratio of the account, is the average payment period ratio of customers, is the customer's account amount, The time when the account is due, The time when the account was generated. The amount of accounts payable for each customer, Is a positive integer.

4. The enterprise financial risk management system based on big data according to claim 3 is characterized by: The method for grouping customers by clustering is: The average payment period ratio of each customer is taken as a data node, and randomly selected data nodes as the initial centroid, represents the number of categories after clustering, is a positive integer, where The initial centroid is expressed as: , Indicates The average payment period ratio of the customers with the data nodes as the initial centroid, is a positive integer, and ; The average payment-to-period ratio of customers is taken as the node feature vector. For the feature vector in each region, its distance to each initial centroid is calculated and assigned to the cluster represented by the nearest centroid. The formula for calculating the distance to the initial centroid is: in, Indicates The initial centroid and The distance between data nodes, Indicates The average payment period ratio of customers corresponding to each data node; For each cluster, after each clustering is completed, the mean of all points in the cluster is recalculated and used as the feature data of the new centroid. The update formula of the centroid feature data is: in, Indicates that the The number of data nodes of the centroid, Indicates that the The average payment period ratio of the customers corresponding to the data nodes of the centroid, represents the mean of the payment-period ratio of the updated centroid; Based on the updated feature vector of the centroid, clustering is performed again until the change of all centroid positions is less than the threshold, then the clustering is considered stable and the clustering is terminated.

5. The enterprise financial risk management system based on big data according to claim 1 is characterized by: The calculation formula for calculating the expected value of the payment-period ratio of each group is: in, is the expected value of the payment period ratio for each group, For each group The average payment period ratio of each customer, is the number of customers in each group, is a positive integer; According to the numerical value of the expected value of the payment period ratio of each group, the groups are sorted in descending order.

6. The enterprise financial risk management system based on big data according to claim 5 is characterized by: The calculation formula for the distribution of accounts receivable amount for each group is: in, For each group, the amount of accounts receivable is distributed. For each group The amount of the account of each customer; The calculation formula of the safety factor of the accounts receivable structure is: in, is the safety factor of the accounts receivable structure, is the number of groups after grouping, After sorting The distribution of accounts receivable amount in each group.

7. According to the enterprise financial risk management system based on big data as claimed in claim 1, it is characterized by: The calculation formula of the customer's reputation is: in, For the credibility of customers, The time when the account is due, The time when the account was generated. The payment collection time. The first Accounts, The number of accounts receivable during the customer account assessment period; The calculation formula of the repayment rate is: in, The repayment rate for the customer, The amount of the customer's accounts receivable during the accounts receivable assessment period. The repayment amount of the customer during the account assessment period; The formula for calculating the customer risk factor based on the credit rating and repayment rate in each cycle is: in, The customer risk factor.

8. The enterprise financial risk management system based on big data according to claim 1 is characterized by: The calculation formula for calculating the account evaluation index based on the account structure safety factor and the customer risk factor is: in, is the accounts receivable valuation index, is the customer risk factor, is the safety factor of the accounts receivable structure, are the weights of customer risk factor and account structure safety factor, respectively. , .

9. The enterprise financial risk management system based on big data according to claim 8, characterized in that: The steps of updating the accounts receivable data at the end of the accounts receivable evaluation cycle are as follows: First, you need to determine the current account receivable balance for each customer. Based on the account generation time, use the first-in-first-out method to offset the account amount with the repayment amount in the order of account generation time from earliest to latest. The formula for calculating the accounts receivable risk coefficient based on the change in the accounts receivable evaluation index is: in, is the mean value of the accounts receivable valuation index, is the fluctuation value of the accounts receivable valuation index, is the account risk factor, For the The accounts receivable valuation index within an accounts receivable valuation cycle, The number of cycles for the receivables assessment; when If the risk is judged to be high, debt collection measures should be taken immediately; in, The threshold for assessing accounts receivable risk.

10. A method for enterprise financial risk management based on big data, characterized by: The enterprise financial risk management method is obtained by executing an enterprise financial risk management system based on big data according to any one of claims 1 to 9, and the specific steps include: Step 1: Obtain the account information data of the enterprise to be managed, and calculate the average collection period of each historical account as the account evaluation period; Step 2: Calculate the customer's payment period ratio based on the account amount, account generation time and account repayment time of each customer's account data. Use the average of the customer's payment period ratio as a feature and group the customers by clustering method. Step 3: Based on the results of customer clustering, sort the clustered groups by calculating the expected value of the payment period ratio of each group, calculate the distribution of the account amount of each group, and calculate the account structure safety factor based on the sorting order of each group; Step 4: Calculate the customer's creditworthiness based on the account generation time, account repayment time, and account collection time of each account in each account assessment cycle of each customer; calculate the repayment rate based on the account amount and repayment amount in the cycle; and calculate the customer risk factor based on the creditworthiness and repayment rate in each cycle; Step 5: Calculate the accounts receivable assessment index based on the accounts receivable structure safety factor and the customer risk factor. Update the accounts receivable data at the end of the accounts receivable assessment cycle, recalculate the accounts receivable assessment index in the new cycle, and calculate the accounts receivable risk factor based on the changes in the accounts receivable assessment index.

Images