Article Preview
TopIntroduction
With the widespread popularity of mobile devices, the booming mobile Internet provides enterprises with more access to customer information, thus promoting the rapid development and broad application of big data, data storage, cloud computing, and other technologies (Lee and Oh, 2020). Besides, AI (artificial intelligence) technology has fast grown, benefiting from the rapid growth of data and the enhancement of computing power (Wang et al., 2020a). In this context, the traditional rural financial industry is facing peer competition within the industry and challenges from the Internet financial industry (Ye et al., 2018). For data-driven business industries such as banks, there are urgent requirements for business according to different demands, including obtaining practical value from the data, conducting business more effectively for various customer groups, exploring the potential value of data, and earning more incredible benefits. Bank enterprises combine data analysis, data mining, and machine learning models with actual business for customer group division, customer churn prediction, customer behavior information analysis, and customer credit prediction division. However, most of these methods are in the stage of research and preliminary application. In the actual production, the use of data is not sufficient and reasonable. Furthermore, the application of big data technology and AI technology in the banking industry is still in its infancy, and there is still much room for development. Rewilak (2017) used AI technology to study whether financial development was conducive to rural poverty reduction. They found that financial deepening and greater physical access are conducive to reducing people below the poverty line. They used alternative measures of economic instability, and the results also challenged existing findings that economic instability may increase the incidence of poverty (Rewilak, 2017). To lessen the complexity and time consumption of traditional statistical and mathematical planning methods, Metawa et al. (2017) used AI technology to conduct research and analysis on rural finance. They proposed an intelligent credit decision model for rural banks based on a genetic algorithm. This model could provide a framework for optimizing bank objectives when constructing loan portfolios and seek dynamic loan decisions by maximizing bank profits and minimizing bank default probability. This model was more intelligent than the previous methods, which could shorten the screening time of bank’s loan by 12% to 50%, and meanwhile increase rural bank profit by 3.9% to 8.1% (Metawa et al., 2017).