Empowering FinTech Revolution with an AI Brain

As emerging value-generating tools, AI and machine learning technologies have benefited from the scientific and efficient methodology and has been widely used in various business scenarios, and can significantly improve the company's performance indicators. Seventy-six percent of businesses said they are using machine learning and have improved their performance goals, and at least 40% use machine learning to improve sales and marketing. Leading Internet companies have provided great capabilities through machine learning technologies. In the area of banking and finance, from approving loans to asset management to risk assessment, machine learning can play critical role in many phases of the financial ecosystem and also leads the wave of innovation in FinTech. Due to the fast-evolving nature of AI technologies and machine learning algorithms, it is difficult for average users to understand and master all the details. Moreover, the machine learning of financial data has the unique type of its industry. Therefore, in order to support efficient and timely application of machine learning technology in the financial sector, an “AI Brain”, a machine-learning platform customized for finance institutes’ business with less steep learning curve is needed. In this talk, I will talk about a work-in-process and lessons learned from designing and implementing an “AI Brain” for a large commercial bank in China. We improve the state-of-the-art by first emphasizing the preservation, standardization and reuse of industrial domain knowledge using its Common Data Model. By integrating the multiple machine learning and deep learning frameworks on top of powerful big data platforms like Spark, our design enable businesses to choose the most appropriate machine learning algorithms to solve their problems at hand. We also provide two ways for user to interact with it: (a) a powerful notebook for data scientist or analyst with advanced programming skills and (b) a visual pipeline that guides intermediate users through common data analytics and modeling scenarios. Varies modeling pipeline templates have been provided, which are designed to guide user with scientific methods and known best practices. In this talk, I will also show cases some of the successful applications in banking which helps the business to lift revenue, fight fraud, improve customer service, or even developing new products.