Big Data Credit and Bank Risk Control Innovation
Data will be one of the core competitiveness of banks in the future, which has become the *** knowledge of the banking industry. In the era of big data, banks are facing competition not only from within the industry, but also increasingly severe external challenges, the Internet, e-commerce and other emerging companies in the product innovation capabilities, market sensitivity and experience in big data processing and so on have obvious advantages. In this situation, the use of big data credit innovation and improve the bank's risk control has gradually become an important topic of concern and discussion in the industry.
Banking industry's shortcomings in risk control
China Financial and Banking Outlook 2015 released by PricewaterhouseCoopers pointed out that by the end of the third quarter of 2014, the total non-performing loans (NPLs) of China's commercial banks had risen by 36% to RMB 767 billion, a high point in four years. The trend of rising NPLs is expected to continue in 2015. Behind the above figures, in addition to the reasons for the rise in overdue risks due to the economic downturn, loopholes and flaws in banks' risk control are also important reasons.
Information asymmetry and loan fraud
With the rise of P2P, microfinance and other private lending, it is increasingly easy for borrowers to obtain loans through non-bank channels. The private lending institutions are not required to report data to the People's Bank of China, the non-banking system of loan applications, liabilities and overdue information such as unclear, non-transparent, can not be foreseen in advance of the contradiction is more and more prominent, often to the borrower overdue or even out of touch, the bank is only passive to understand the borrower in the field of private lending part of the history of overdue borrowing or liabilities, such as excessive information on bad behavior.
Loan fraud is also another problem faced by banks, especially in the field of credit cards and some of the use of credit factory model operation of the loan products. It is no longer a secret that banks have solidified their card-issuing review process and the credit factory model of operation. At present, the packaging of credit cards and loans, group fraud and fraudulent loans are common, especially in the field of credit loans, about 60% of credit loans come from fraud, which is more than half due to identity fraud and data packaging. In the absence of comprehensive data dimensions, banks and other lending institutions are prone to be exploited by group fraudulent lenders due to the lack of third-party big data support and the lack of adequate and effective means of cross-checking.
Intimely information and post-loan risk prevention
Intimely access to information has also brought different degrees of trouble to banks in post-loan risk management. For example, banks often want to be the first to know whether a corporate customer is facing new legal action after obtaining a loan, but most banks use a method that relies only on the credit manager to manually check the local court website from time to time to obtain the information, which is subject to great uncertainty, and once the credit manager forgets to check or makes a mistake, the monitoring of post-loan judicial litigation will be virtually null and void. This does not include the continuous monitoring of the customer's application, indebtedness and delinquency in private lending and other risk points. The means and efficiency of the bank in the process of post-loan risk prevention have greatly restricted the effectiveness of the bank's risk control.
The contradiction between cost and efficiency
In order to solve the problem of information asymmetry and the problem of untimely access to information, banks often need to collect a large amount of data to assist in judgment. However, the usual method of data collection is to ask the borrower or enterprise to provide a large amount of additional information, which involves a large amount of labor costs and time costs. In order to improve efficiency, it is necessary to build a set of automated data collection, as well as a high degree of automation of the back-end management system, but this must set up a specialized team of engineers and a large number of IT development work, many small and medium-sized banks is also a heavy burden.
Big Data Credit and Loan Risk Control
The Rise of the Big Data Credit Industry
In January 2015, the People's Bank of China (PBOC) issued a Notice on Preparation for Personal Credit Business, which required eight organizations, including Sesame Credit Management Co. Ltd. and Lakala Credit Management Ltd. to make preparations for personal credit collection business for a period of six months. This means that these eight organizations may become the first batch of commercial personal credit agencies in China. As a result, the prelude to the big data credit collection industry has been officially opened, and the growth space of the personal credit collection market has been opened. Based on the U.S. personal credit market of 60 billion U.S. dollars, taking into account the huge population base in China, the future development of China's personal credit market space after maturity is likely to reach 100 billion yuan scale.
It is worth noting that the big data credit has become the Internet giants must fight. In addition to Alibaba and Tencent, Baidu, Jingdong Finance, Xiaomi Finance, 360 Finance and other Internet companies have also said that they will build an Internet credit system and are interested in applying for the second batch of personal credit licenses, and some of these institutions have already submitted applications to the People's Bank of China. The high-profile involvement of Internet companies shows that, on the one hand, the innovative characteristics and rapid expansion characteristics of Internet companies have brought new vitality and opportunities to the traditional credit field, and on the other hand, the different big data advantages and application scenarios advantages of Internet companies will make the competition in the credit market increasingly white-hot.
The development trend of domestic big data credit collection industry
The involvement of various types of big data companies in the big data credit collection market has greatly enriched the dimensions and types of data compared with two years ago. In particular, with the rise of the mobile Internet era, big data companies and big data services centered around mobile Internet device information, geographic location information, and carrier information have emerged in an endless stream and have begun to be used in the P2P loan review and cross-checking process. However, the source and validity of the data still restricts the development of the big data credit industry, the industry is still in the early stage of exploration, there is no mature "killer" application tools.
Information silos still exist. Information silos are an important constraint on the development of the domestic credit industry. Information asymmetry and non-transparency have brought about a large number of multiple liability risks and fraud risks. In the rise of the domestic big data credit industry, the market has placed great expectations on eliminating information opacity and breaking information silos. From the current development of the industry, the information silos can not completely disappear in the short term.
First of all, information on public **** utility payments, fixed assets, social security, residence and other information closely related to loan risk control is still attributed to the relevant government departments. Although information on industry and commerce, justice and other information has been opened to the community, the degree of openness of government information is still low, which will be a long-term and complex process.
Second, it is difficult for Internet companies that hold a large amount of citizens' information to interoperate with each other. At present, the domestic social data, e-commerce data, geographic location data, search data, mobile device usage behavior data and other Internet information are concentrated in the hands of Ali, Baidu, Tencent, Jingdong, 360 and other Internet giants, these companies in the process of running a large number of competitive relationships, data interoperability, information **** enjoy the possibility of the current situation seems extremely low.
Finally, it is also difficult to interoperate information between credit bureau companies. The core competitiveness of a credit bureau is to have its own unique information. As direct competitors, it is impossible for credit bureaus to use their own core data to enhance the competitiveness of their competitors. It can be said that, on the one hand, credit collection companies are committed to solving information asymmetry, on the other hand, credit collection companies are also building data barriers.
Application scenarios are gradually enriched, and combined credit assessment may become mainstream. Looking at the more developed credit industry in the United States, the use of credit reports has long been not only limited to the financial sector, such as recruitment, rental housing, car rental, dating and other industries and fields need to use personal credit reports. With the promotion of "Internet+", the concept of big data and the development of P2P Internet finance, domestic credit reporting companies are also exploring and experimenting with the richness of application scenarios.
From the point of view of the current development of the domestic big data credit collection industry, due to the information silos, data incomplete **** enjoy the status quo will exist for a long time, when the industry develops to a certain stage, it will produce a combination of credit assessment. For example, the person concerned is required to produce credit reports from multiple agencies at the same time, and make a holographic user portrait of the person concerned from different perspectives, such as social networking, e-commerce, recruitment, browsing behavior, and geographic location, in order to judge his or her comprehensive situation. This is because a one-sided credit assessment can no longer fully evaluate a person, and the information strengths of each big data credit company must be brought into play in order to make a comprehensive evaluation.
Application cases of big data credit in the field of loan risk
Sesame Credit, which reflects the credit behavior of e-commerce. Sesame Credit is based on Alibaba's e-commerce transaction data and Ant Gold Service's Internet financial data, and establishes data cooperation with public **** organizations such as Public Security Network and partners, with data covering credit card repayments, online purchases, money transfers, financial management, water, electricity, and coal payments, rental information, address relocation histories, and social relationships, among others. Sesame Credit uses the Sesame Score to visualize the credit level, which mainly contains five dimensions: users' credit history, behavioral preferences, fulfillment ability, identity traits, and connections, and is divided into five grades from 950 to 350, with higher scores representing better creditworthiness and a lower likelihood of default. Sesame Credit also produces personal credit reports, which are mainly provided by the central bank's credit center and record basic personal information, loan information, credit card information and credit report inquiry records.
Tencent Credit, which reflects Internet social behavior. Tencent Credit's data is more social data, and its credit products have two major categories: first, anti-fraud products, including face recognition and fraud evaluation; and second, credit rating products, including credit scores and credit reports. The main service targets of Tencent's anti-fraud credit products include banks, securities, insurance, consumer finance, microfinance, P2P and other commercial institutions, which can help companies identify users' identities, guard against shady accounts or organized fraud, and detect malicious or suspected fraudulent customers to avoid financial losses. For users such as blue-collar workers, students, self-employed people and freelancers who did not have personal credit reports before, Tencent builds personal credit scores for them through their use of services such as social networking, portals, games, and payments by using massive data mining and analysis techniques to predict their risk performance and credit worthiness.
Good Loan Cloud wind control that reflects the risk of borrowers. Good Loan Cloud Wind Control is a big data wind control platform built by Good Loan and FICO (FICO)***, the world's largest personal credit scoring organization, integrating important data sources such as credit bureau, judicial data, industrial and commercial data, consumer data, etc., and constructing risk databases in all fields of the whole industry required for financial and lending institutions to carry out wind control, and at the same time including data from the anti-fraud risk list database, the significant risk identification list database, and the loan application Record list database data, which together have exceeded 70 million items. The database of more than 6,000 dimensions can not only effectively complement the local database of lending institutions, but also assist them to significantly improve anti-fraud identification and credit risk identification capabilities, while combining with FICO's credit decision engine to provide services to credit institutions. Financial institutions no longer need to invest heavily in building their own systems, or spend huge efforts and costs to find all kinds of risk control data.
The combination of bank risk control and big data credit
Big data can hardly solve all problems, but it can be used as an effective tool. What value can big data bring to the credit industry? The author's judgment is: big data in the coming period of time, still can not solve all the problems in credit risk control; or simply rely on big data for credit risk control, approval of the whole process of the type of loan is still very limited.
But big data can already solve part of the credit industry, and will play an increasingly important role. For example, big data has been increasingly used in conducting anti-fraud identification, risk dynamic monitoring, user behavior analysis, user profiling and other areas. Banking institutions should embrace big data, and dare and be good at using big data to assist in risk control.
Through big data, private lending information is transparent to banks. Banking institutions can understand the borrower's information on private lending through data from big data credit. At present, the information related to private lending provided by big data credit companies mainly contains blacklist information, loan application information and queried information. Taking the good loan cloud wind control as an example, it contains the blacklist information of various credit collection companies as well as the blacklist information of dozens of P2P platforms integrated by the good loan cloud wind control platform, and also contains the 10 million loan application records of the good loan network and the queried information that doubles every week. All of this information reflects the borrower's private lending situation from the side. Through big data credit, it will be able to make private lending information more and more transparent to banking institutions, identify more private lending risks, and conduct better loan audits and anti-fraud identification.
Enriching data dimensions, improving the ability of credit file clientele wind control. 2014, the U.S. Policy and Economic Research Council (PERC) study on the role of non-financial information (which has also become alternative information) in credit decision-making showed that the inclusion of non-financial information, such as water, electricity, coal, cable TV, cell phones and other non-financial information in the credit collection system has significantly improved the ability of people with credit files to obtain credit. ability.
At present, many banks have gradually realized that the amount of information that has been included in the bank's traditional database is not rich and complete, and have begun to actively engage with third-party big data credit companies to frequently contact and approach cooperation, such as customer information, the bank has the customer's basic identity information. However, other customer information, such as personality traits, interests, habits, industry sectors, living conditions, etc. is difficult for banks to accurately grasp; on the other hand, the analysis of a variety of heterogeneous data is difficult to deal with, such as the bank has the customer's information on the flow of funds, behavioral information on web browsing, voice information on service calls, business halls, ATM video information, but in addition to structured data, the other data can not be analyzed, let alone talk about the structured data, the other data can not be analyzed. However, except for structured data, other data cannot be analyzed, not to mention the comprehensive analysis of multiple information, which makes it impossible to break the pattern of "information silos". Through the cooperation with third-party big data credit companies, we try to make up for our own shortcomings in the dimension of information acquisition as well as the ability of data mining and analysis.
In summary, the author believes that in the context of the Internet era and the era of big data, if banks want to further accelerate the pace of transformation, realize the vision of an honest society and financial inclusion, and shoulder the heavy responsibility of credit risk management, they should take advantage of the Internet in the use of information, pre-credit investigations, monitoring and control of loans and other aspects of risk control, embrace the advantages of big data credit collection, and make full use of all kinds of information inside and outside to do a good job in the collection of customer credit and credit enhancement, and further improve the risk management. Credit enhancement, to further improve the level of risk control and management, in order to be invincible.
The above is what I share with you about the big data credit and bank risk control innovation, more information can be concerned about the Global Green Ivy to share more dry goods