A method for analyzing bank and insurance data

Abstract

The invention discloses a bank insurance data analysis method, which relates to the technical field of data processing. The bank insurance data analysis method comprises the following steps: S1, collecting bank insurance data, and performing standardization processing on the bank insurance data to obtain the customer identity authentication rate and data consistency ratio; S2, performing data cleaning and preprocessing on the bank insurance data to obtain the transaction record error rate and data update frequency; S3, establishing a bank insurance database to obtain the customer duplicate item ratio; S4, obtaining the insurance data quality assessment value according to the data quality original score and the first threshold comprehensive analysis; S5, comparing the insurance data quality assessment value with the second threshold to obtain the insurance data quality assessment report, and specifying corresponding optimization processing measures according to the insurance data quality assessment report. The problem of inconsistent data quality caused by the diversification of bank insurance data sources and uneven data quality is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a banking and insurance data analysis method. Background Art

[0002] With the rapid development of information technology, the banking and insurance industries have accumulated a large amount of data, including but not limited to customer information, transaction records, insurance claim records, etc. Effectively managing and analyzing this data is of great significance for improving service quality, optimizing risk management, and enhancing decision support. However, due to the large amount of data, diverse sources, and uneven quality, how to effectively integrate, clean, analyze, and extract valuable information from this data has become a challenge.

[0003] In the existing technology, traditional data processing methods often involve complicated manual operations, which are not only inefficient, but also prone to human errors affecting data quality. In addition, the lack of a systematic data quality assessment mechanism makes it difficult for banks and insurance institutions to accurately assess the true value and reliability of their data assets.

[0004] Therefore, in response to the above problems, a banking and insurance data analysis method is urgently needed. Summary of the invention

[0005] Technical issues solved

[0006] In view of the deficiencies of the prior art, the present invention provides a bank insurance data analysis method, which solves the problem of inconsistent data quality caused by the diversification of bank insurance data sources and uneven data quality.

[0007] Technical Solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: a bank insurance data analysis method, comprising the following steps: S1, collecting bank insurance data, and standardizing the bank insurance data to obtain customer identity authentication rate and data consistency ratio; S2, cleaning and preprocessing the bank insurance data to obtain transaction record error rate and data update frequency; S3, establishing a bank insurance database to obtain customer duplicate item ratio; S4, obtaining the original data quality score through comprehensive analysis of customer identity authentication rate, data consistency ratio, transaction record error rate, data update frequency and customer duplicate item ratio, and obtaining the insurance data quality assessment value through comprehensive analysis based on the original data quality score and a first threshold; S5, comparing the insurance data quality assessment value with the second threshold to obtain an insurance data quality assessment report, and specifying corresponding optimization processing measures according to the insurance data quality assessment report.

[0009] Furthermore, the specific process of collecting bank insurance data and standardizing the bank insurance data is as follows: collecting bank insurance data, formatting and verifying the bank insurance data according to a predetermined format and standard, marking the number of customers who have passed the verification and the total number of customers, and obtaining the customer identity verification rate by calculating the ratio of the number of customer information that has passed the verification to the total number of customers; using data loading tools and data quality monitoring tools to check the consistency of account information in the bank insurance data, and recording the number of accounts with consistent data and the total number of customer accounts, and obtaining the data consistency ratio by calculating the ratio of the number of accounts with consistent data to the total number of customer accounts.

[0010] Furthermore, the specific process of data cleaning and preprocessing of the bank insurance data to obtain the transaction record error rate and data update frequency is as follows: removing invalid and erroneous data entries in the bank insurance data, and recording the number of erroneous transaction records and the total number of transaction records at the same time, and obtaining the transaction error record rate by calculating the ratio of the number of erroneous transaction records to the total number of transaction records; correcting inconsistencies in the data by adjusting the format and unit in the bank insurance data, and excluding deviated data points in the bank insurance data; recording the timestamp of the bank insurance data update, and recording the data update frequency.

[0011] Furthermore, the specific process of establishing a bank insurance database and obtaining the customer duplicate ratio is: collecting bank insurance data to establish a bank insurance database, and using data deduplication technology to identify and merge duplicate customer records, recording the number of duplicate records and the total number of customer records; and obtaining the customer duplicate ratio by calculating the ratio of the number of duplicate records to the total number of customer records.

[0012] Furthermore, the specific process of obtaining the original data quality score through comprehensive analysis of customer identity authentication rate, data consistency ratio, transaction record error rate, data update frequency and customer duplicate item ratio is as follows: obtaining the customer identity authentication rate, data consistency ratio, transaction record error rate, data update frequency and customer duplicate item ratio, and obtaining the original data quality score based on comprehensive analysis of the customer identity authentication rate, data consistency ratio, transaction record error rate, data update frequency and customer duplicate item ratio.

[0013] Furthermore, the specific calculation process of the data quality raw score is:

[0014] RS=w1×C+w2×C s +w3×A+w4×T, where RS represents the original score of data quality, C represents the customer identity verification rate, w1 represents the customer identity verification rate weight factor, and C represents the customer identity verification rate weight factor. srepresents the account data consistency ratio, w2 represents the account data consistency ratio weight factor, A represents the transaction record error rate, w3 represents the transaction record error rate weight factor, T represents the data update frequency, and w4 represents the data update frequency weight factor.

[0015] Furthermore, the specific calculation formula of the insurance data quality assessment value is:

[0016] In the formula, DS represents the insurance data quality assessment value, RS represents the original score of data quality, β represents the formula curve adjustment parameter, and θ represents the first threshold.

[0017] Furthermore, the insurance data quality assessment value is compared with the second threshold to obtain the insurance data quality assessment report. The specific process is: real-time comparison of the insurance data quality assessment value and the second threshold. When the insurance data quality assessment value is greater than or equal to the second threshold, it indicates that the quality of the bank insurance data is good; when the insurance data quality assessment value is less than or equal to the second threshold, it indicates that the quality of the bank insurance data is poor.

[0018] Furthermore, the specific process of specifying corresponding optimization processing measures according to the insurance data quality assessment report is: when the insurance data quality assessment value is greater than or equal to the second threshold, no adjustment is made; when the insurance data quality assessment value is less than or equal to the second threshold, the frequency of comparing the insurance data quality assessment value with the second threshold is increased, and the standardization processing, data cleaning and preprocessing of the bank insurance data are repeated until the insurance data quality assessment value rises above the second threshold.

[0019] Furthermore, the specific process of collecting bank insurance data and establishing a bank insurance database is: collecting bank insurance data, importing the bank insurance data into the database through extraction, conversion and loading processes, thereby establishing a bank insurance database.

[0020] Beneficial Effects

[0021] The present invention has the following beneficial effects:

[0022] (1) This bank and insurance data analysis method effectively improves the accuracy and consistency of bank and insurance data through systematic data standardization processing and cleaning preprocessing. The calculation of customer identity authentication rate and data consistency ratio ensures the integrity of the data, reduces the impact of errors and duplicate data, thereby improving the reliability of data processing, and further achieves a significant improvement in data integrity and consistency, effectively solving the problem of data unreliability caused by data errors and duplications in the prior art.

[0023] (2) This banking and insurance data analysis method can monitor and evaluate data quality in real time by establishing a comprehensive data quality evaluation system, and calculate the data quality raw score based on customer identity authentication rate, data consistency ratio, transaction record error rate, data update frequency and customer duplicate item ratio. This achieves the effect of continuous monitoring of data quality, and effectively solves the problem of lack of timely data quality feedback and monitoring mechanism in the prior art.

[0024] (3) This banking and insurance data analysis method generates a data quality assessment report by comparing the data quality assessment value with a preset threshold value, and specifies corresponding optimization processing measures based on the report. This dynamic optimization mechanism not only ensures that the data continues to meet the high standards of business needs, but also promotes the continuous improvement of business processes and decision support, thereby achieving dynamic adjustment and continuous optimization of the data processing process, and effectively solving the problem of rigidity and lack of flexibility of the data processing process in the prior art.

[0025] (4) This banking and insurance data analysis method enhances the data-based decision-making process by ensuring the high quality and accuracy of the data. High-quality data supports accurate analysis, provides a solid data foundation for key decisions, improves the accuracy and effectiveness of decisions, and thus achieves the effect of relying on high-quality data in the decision-making process, effectively solving the problem of inaccurate decision-making caused by poor data quality in the prior art.

[0026] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a structural diagram of a banking and insurance data analysis method of the present invention. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] See also Figure 1Figure, an embodiment of the present invention provides a technical solution: a bank insurance data analysis method, comprising the following steps: S1, collecting bank insurance data, and standardizing the bank insurance data to obtain customer identity authentication rate and data consistency ratio; S2, cleaning and preprocessing the bank insurance data to obtain transaction record error rate and data update frequency; S3, establishing a bank insurance database to obtain customer duplicate item ratio; S4, obtaining a data quality raw score through comprehensive analysis of customer identity authentication rate, data consistency ratio, transaction record error rate, data update frequency and customer duplicate item ratio, and obtaining an insurance data quality assessment value based on a comprehensive analysis of the data quality raw score and a first threshold; S5, comparing the insurance data quality assessment value with the second threshold to obtain an insurance data quality assessment report, and specifying corresponding optimization processing measures according to the insurance data quality assessment report.

[0030] Specifically, the specific process of collecting and standardizing bank insurance data is as follows: First, systematically collect bank insurance data. This step involves obtaining data from multiple data sources (including internal systems such as customer relationship management systems, insurance claims processing systems, and external data sources such as public data sets and information provided by partners). The collected data is formatted and verified according to predetermined formats and standards to ensure data consistency and accuracy. This process includes unifying the date format, currency unit and other relevant information of the data, while performing quality checks on the data, identifying and processing any incomplete or erroneous records.

[0031] After data standardization, the number of verified customers and the total number of customers are marked. This step is achieved by calculating the ratio of the number of verified customer information to the total number of customers, thereby obtaining the customer identity verification rate. This rate is an important indicator for measuring data integrity and reflects the success rate of customer information verification in the data set.

[0032] Next, use data loading tools and data quality monitoring tools to check the consistency of account information in the bank and insurance data. This includes checking the consistency of account information, such as ensuring that the customer's account records are represented consistently in different systems. In this way, the number of accounts with consistent data and the total number of accounts are recorded, and the data consistency ratio is calculated. This ratio is a key indicator of the overall consistency of the data, indicating the degree of alignment of account information in the data.

[0033] In this implementation plan, the standardization level and quality of bank and insurance data are effectively improved, ensuring the integrity and consistency of the data. By accurately calculating the customer identity verification rate and data consistency ratio, this step makes the data more reliable and accurate, providing a solid foundation for subsequent analysis and decision-making. This step significantly optimizes the data management process, reduces the risks brought by erroneous data, and further enhances the efficiency and effectiveness of data-driven decision-making. The specific process of cleaning and preprocessing bank and insurance data to obtain the transaction record error rate and data update frequency is as follows:

[0034] Specifically, the first step is to remove invalid and erroneous data entries, which is crucial to ensure the accuracy of the data. Through careful data review and cleaning, erroneous transaction records are identified and removed from the data set. At the same time, the system records the number of erroneous transaction records removed and the total number of transaction records in the data set. In this way, by calculating the ratio of the number of erroneous transaction records to the total number of transaction records, the transaction error record rate is obtained. This ratio is a key indicator for evaluating the quality of data processing and reflects the efficiency and accuracy of the data cleaning process.

[0035] Next, the data format and unit are standardized, which includes adjusting the date format, currency unit and other related information in the bank and insurance data to ensure the consistency of all data in the database. In this step, data points that obviously deviate from the normal range will also be excluded, such as outlier processing, to further improve the availability and consistency of the data.

[0036] Finally, record the update timestamp of bank and insurance data to monitor the freshness and timeliness of the data. The system automatically records the specific time of each data update and calculates the data update frequency accordingly. By continuously tracking the frequency of data updates, you can ensure that the data remains up to date and help the analysis team adjust the data processing strategy and analysis model in a timely manner to adapt to the latest data changes.

[0037] In this implementation plan, through this series of data cleaning and preprocessing measures, the accuracy and consistency of bank and insurance data are effectively improved. These steps ensure the reduction of errors and invalid entries in the data, while standardizing the data format and units, reducing the impact of data deviations and outliers. In addition, by monitoring and recording the frequency of data updates, the timeliness and update of the data are guaranteed. Overall, these measures significantly improve the quality and reliability of the data, providing a solid data foundation for subsequent analysis and decision-making.

[0038] Specifically, the data quality raw score is obtained through comprehensive analysis of customer identity authentication rate, data consistency rate, transaction record error rate, data update frequency and customer duplicate item rate. The specific process is as follows:

[0039] The first step is to obtain key data quality indicators, including customer identity verification rate, data consistency ratio, transaction record error rate, data update frequency and customer duplicate ratio. These indicators are obtained through precise data measurement and recording, and each indicator reflects a specific quality aspect of the data set. The customer identity verification rate shows the proportion of verified customer information in the data, which is an important indicator for measuring data integrity. The data consistency ratio evaluates the consistency level of each account information in the data, and the key is to ensure the credibility of the data. The transaction record error rate reveals the proportion of problematic records in the transaction data, which directly affects the accuracy of the data. The data update frequency indicates the ability of the data to stay up to date, which is crucial for the dynamic environment of the banking and insurance industry. The customer duplicate ratio points out the situation of duplicate records in the data, which affects the uniqueness and efficiency of data use.

[0040] Next, we conduct a comprehensive analysis based on these acquired data quality indicators. We weight and synthesize the customer identity verification rate, data consistency ratio, transaction record error rate, data update frequency, and customer duplicate ratio through a specific mathematical model and algorithm to calculate a comprehensive data quality raw score. This score is a quantitative representation that comprehensively reflects the performance of the data set in different quality dimensions and is a key indicator for evaluating overall data quality. Through such analysis, we can systematically identify quality problems in the data and directions for improvement, providing a scientific basis for subsequent data processing and quality improvement measures.

[0041] In this implementation plan, by obtaining and comprehensively analyzing key data quality indicators such as customer identity authentication rate, data consistency ratio, transaction record error rate, data update frequency and customer duplicate ratio, this step effectively quantifies the overall quality of the data and generates a raw data quality score. This score provides a clear benchmark for further data quality assessment, helps identify and prioritize key data quality issues, and thus promotes improved data management and accurate decision-making.

[0042] Specifically, the calculation process of the raw score of data quality is: RS = w1×C+w2×C s +w3×A+w4×T, where RS represents the raw score of data quality, C represents the customer identity verification rate, which measures the accuracy of verified customer information in the data set; w1 represents the customer identity verification rate weight factor, which determines the influence of this indicator in the total score; C sIt represents the account data consistency ratio, which reflects the consistency degree of different account information in the data; w2 represents the account data consistency ratio weight factor, A represents the transaction record error rate, this indicator reveals the proportion of problematic records in the transaction data; w3 represents the transaction record error rate weight factor, T represents the data update frequency, this indicator reflects the ability of the data to keep updated, w4 represents the data update frequency weight factor, these factors can be obtained through analysis of historical data.

[0043] In this implementation, by carefully setting the weight factors of data quality assessment, this step effectively ensures that the scoring model can accurately reflect the real impact of each data quality indicator on the overall data quality. By adjusting the weights, the flexibility and adaptability of the evaluation system are enhanced, making data quality management more accurate and targeted. This method not only improves the efficiency of the data processing process, but also optimizes the decision-making process based on data.

[0044] Specifically, the specific calculation formula for the insurance data quality assessment value is: Where, the insurance data quality assessment value represents the insurance data quality assessment value, which is a value from 0 to 1 that is used to measure the quality of the overall data. A high insurance data quality assessment value indicates high data quality, while a low value indicates low data quality. RS represents the raw score of data quality, which is calculated based on the various data quality indicators collected in the previous steps, β represents the formula curve adjustment parameter, which determines the steepness of the function curve, thereby affecting the sensitivity of the assessment value to the raw score, and θ represents the first threshold, which sets the benchmark point of data quality.

[0045] In this implementation, the overall quality of the data is accurately quantified by using the insurance data quality assessment formula, making the data quality assessment more dynamic and detailed. This step effectively solves the problem of the difficulty in accurately assessing data quality in the prior art, and provides a scientific and reliable basis for subsequent data processing and business decision-making.

[0046] Specifically, the insurance data quality assessment value is compared with the second threshold to obtain the insurance data quality assessment report. The specific process is as follows: when the insurance data quality assessment value is greater than or equal to the second threshold, the system will generate a report indicating that the quality of the bank insurance data is good. This means that the data meets or exceeds the preset quality standards and can be trusted and used for further business analysis and decision-making. In this case, immediate intervention or improvement measures are usually not required.

[0047] On the contrary, when the insurance data quality assessment value is less than or equal to the second threshold, the report will point out that the quality of bank insurance data is poor. This is a warning signal, indicating that there are quality problems with the data, which may affect the accuracy and reliability of business decisions. In this case, corresponding improvement measures need to be taken, such as data cleaning again, re-evaluating the reliability of data sources, or adjusting data processing procedures, etc., to improve data quality to an acceptable level.

[0048] In this implementation, by comparing the insurance data quality assessment value with the second threshold in real time, this step effectively monitors and identifies the state of data quality. When the data quality exceeds the threshold, it is confirmed that the data quality is good and suitable for further analysis and decision-making; when it is below the threshold, the data quality problem is identified, prompting timely improvement measures. This method ensures continuous monitoring and quality control of data, improves the reliability of data utilization and the accuracy of decision-making.

[0049] Specifically, the specific process of specifying corresponding optimization measures according to the insurance data quality assessment report is as follows: In the insurance data quality management process, the comparison between the insurance data quality assessment value and the second threshold is a crucial step. Specifically, when the insurance data quality assessment value is greater than or equal to the second threshold, the system will consider that the data quality has reached or exceeded the expected standard, so no adjustment will be made and the existing data processing and management process will be maintained. This indicates that the current data management strategy is effective, the data quality is acceptable, and it is suitable for subsequent business analysis and decision support.

[0050] On the contrary, when the insurance data quality assessment value is less than or equal to the second threshold, this indicates that the data quality does not meet the required standards, which may affect the effectiveness of data use and the accuracy of decision-making. In this case, the system will automatically take measures to improve data quality, first of all, increasing the frequency of comparison between the insurance data quality assessment value and the second threshold in order to more closely monitor changes in data quality. In addition, the system will repeat the standardization, data cleaning and preprocessing steps of bank insurance data. These steps include reformatting the data to ensure consistency, removing errors and invalid data entries, and updating outdated information to systematically improve the accuracy and availability of the data. This process will continue until the insurance data quality assessment value exceeds the second threshold again to ensure that the data meets higher quality standards.

[0051] In this implementation, this dynamic quality control mechanism ensures that data is always used in the best condition, effectively improving the reliability of data and the quality of decision support, thereby enhancing the operational efficiency and decision security of the entire insurance business.

[0052] Specifically, the specific process of collecting bank insurance data and establishing a bank insurance database is as follows: The first step is to collect bank insurance data. This step covers the collection of necessary data from various data sources such as customer information systems, transaction records, policy details, and claims data. After data collection, the next key data processing stage is through the extraction, transformation, and loading (ETL) process. In the extraction stage, the data is extracted from its original location; then in the transformation stage, the data will undergo necessary cleaning and formatting to ensure data quality and consistency; finally, in the loading stage, these processed data will be imported into the bank insurance database.

[0053] In this implementation, this process ensures the integrity and availability of data, enabling the bank and insurance database to support various business needs, including risk assessment, customer relationship management, financial analysis, etc. The establishment of such a database not only improves the efficiency of data management, but also enhances the security and standardization of data, providing banks and insurance companies with a powerful data support system, thereby optimizing the overall business operations and decision-making process.

[0054] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0055] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A banking and insurance data analysis method, characterized in that: The following steps are involved: S1, collect and standardize bank and insurance data to obtain customer identity verification rate and data consistency ratio; S2, perform data cleaning and preprocessing on bank and insurance data to obtain transaction record error rate and data update frequency; S3, establish a bank insurance database and obtain the customer duplication ratio; S4, obtain the data quality raw score through comprehensive analysis of customer identity authentication rate, data consistency rate, transaction record error rate, data update frequency and customer duplicate item rate, and obtain the insurance data quality assessment value through comprehensive analysis based on the data quality raw score and the first threshold; S5, comparing the insurance data quality assessment value with the second threshold value to obtain an insurance data quality assessment report, and specifying corresponding optimization measures according to the insurance data quality assessment report; The specific calculation process of the data quality raw score is: In the formula, represents the raw score of data quality, represents the customer authentication rate, represents the customer identity verification rate weight factor, Represents the account data consistency ratio, Represents the weight factor of the account data consistency ratio, Indicates the transaction record error rate, Represents the transaction record error rate weight factor, Indicates the data update frequency, Represents the data update frequency weight factor; The specific calculation formula of the insurance data quality assessment value is: In the formula, represents the insurance data quality assessment value, represents the original score of data quality, β represents the adjustment parameter of the formula curve, and θ represents the first threshold; The insurance data quality assessment value is compared with the second threshold value to obtain the insurance data quality assessment report. The specific process is: Compare the insurance data quality assessment value with the second threshold in real time, and when the insurance data quality assessment value is greater than or equal to the second threshold, it indicates that the bank insurance data quality is good; When the insurance data quality assessment value is less than or equal to the second threshold, it indicates that the quality of bank insurance data is poor; The specific process of specifying corresponding optimization measures according to the insurance data quality assessment report is as follows: When the insurance data quality assessment value is greater than or equal to the second threshold, no adjustment is made; When the insurance data quality assessment value is less than or equal to the second threshold, the frequency of comparing the insurance data quality assessment value with the second threshold is increased, and the standardization, data cleaning and preprocessing of the bank insurance data are repeated until the insurance data quality assessment value rises above the second threshold.

2. A banking and insurance data analysis method according to claim 1, characterized in that: The specific process of collecting bank insurance data and standardizing the bank insurance data is as follows: Collect bank insurance data, format and verify the bank insurance data according to the predetermined format and standards, mark the number of customers who have passed the verification and the total number of customers, and obtain the customer identity verification rate by calculating the ratio of the number of customer information that has passed the verification to the total number of customers; Use data loading tools and data quality monitoring tools to check the consistency of account information in bank and insurance data, and record the number of accounts with consistent data and the total number of customer accounts. The data consistency ratio is obtained by calculating the ratio of the number of accounts with consistent data to the total number of customer accounts.

3. A banking and insurance data analysis method according to claim 1, characterized in that: The specific process of cleaning and preprocessing the bank insurance data to obtain the transaction record error rate and data update frequency is as follows: Remove invalid and erroneous data entries from bank and insurance data, record the number of erroneous transaction records and the total number of transaction records, and calculate the ratio of erroneous transaction records to the total number of transaction records to obtain the transaction error record rate; Correcting inconsistencies in the data by adjusting the format and units in the bancassurance data and excluding outlier data points in the bancassurance data; Record the timestamp of bank and insurance data updates and the frequency of data updates.

4. A banking and insurance data analysis method according to claim 1, characterized in that: The specific process of establishing a bank insurance database and obtaining the customer duplicate ratio is as follows: Collect bank and insurance data to establish a bank and insurance database, use data deduplication technology to identify and merge duplicate customer records, and record the number of duplicate records and the total number of customer records; The customer duplicate ratio is calculated by calculating the ratio of duplicate records to the total number of customer records.

5. A banking and insurance data analysis method according to claim 1, characterized in that: The specific process of obtaining the data quality raw score through comprehensive analysis of customer identity authentication rate, data consistency rate, transaction record error rate, data update frequency and customer duplicate item rate is as follows: Obtain customer identity authentication rate, data consistency ratio, transaction record error rate, data update frequency and customer duplicate ratio, and obtain the original data quality score based on comprehensive analysis of customer identity authentication rate, data consistency ratio, transaction record error rate, data update frequency and customer duplicate ratio.

6. A banking and insurance data analysis method according to claim 4, characterized in that: The specific process of collecting bank insurance data and establishing a bank insurance database is as follows: Collect bancassurance data and import the bancassurance data into the database through the extraction, transformation and loading process to build bancassurance database.

Images