We will share our practice of applying AI in finance. Predicting financial risk is a long-lasting challenge in consumer finance industry. Existing predictive models mainly rely on structured credit data but fail to work on unstructured non-financial data. A few studies that work on non-financial data usually focus on merely one data source. We follow a design science approach and propose a framework to predict financial risk within multiple non-financial data sources (i.e. within-app browsing behavior, short message, and customer social network). Based on the kernel theory of Predictive Analytics, we detail a design framework which first develops individual predictive models within each data domain and then ensembles them together for a multifaceted risk profiling. We conduct multiple experiments to evaluate the performance of this framework and find empirical support.
Mingjie Zhu is the founder and CEO of CraiditX. CraiditX is committed to the realization of industrial intelligence through AI technology, and has become the full-time AI partner for Industrial and Commercial Bank of China, China Construction Bank, Bank of Communications, China Merchants Bank, Shanghai Pudong Devolopment Bank etc. It has become the benchmark and leader of AI in the financial industry. Currently, he is also a Researcher in Pengcheng Cyberspace Laboratory (Shenzhen) and an executive director of the AI Young Scientists Alliance. He also serves as a part-time tutor or visiting professor at several universities including the Chinese University of Hong Kong, Fudan University, and the University of Florida. Mingjie Zhu graduated from Special Class for Gifted Young in the University of Science & Technology of China (USTC), and obtained his PhD from the Joint PhD Program launched by Microsoft Research Asia and USTC. After graduation, he conducted postdoctoral research at Max Planck Institute with Dr. Gerhard Weikum. He has more than 10 years of experience in AI research and development. In 2018, Mingjie Zhu was recognized as one of the 35 innovators under 35 by MIT Technology Review.