China‘s First Natural Language-based AI Chatbot Trader

Dr. James Zhang

Bio: Dr. James Zhang is the Managing Director of AI Prediction and Strategy Platform of Ant Group. Dr. Zhang obtained his Ph.D. degree from Univ. of Ottawa, Canada in Electrical Engineering, and both his Master’s and Bachelor degrees from Zhejiang Univ., China. Before he joined Ant Financial, Dr. Zhang worked on finance-related AI at Bloomberg, helped setting up the AI branch of Bloomberg Labs and initiating the GPU computation farm of Bloomberg. Dr. Zhang worked in various areas including image processing, natural language processing, pattern recognition, high-speed hardware development, optical networks, operations research, biometrics, and financial systems.

Title: China‘s First Natural Language-based AI Chatbot Trader


The repurchase agreement, or ‘repo‘, market is an important part of the financial system. Repo is a short-term secured loan, where one party sells securities to another and agrees to repurchase those securities (as collateral) later at a higher price. The repo market allows financial institutions that own lots of securities to borrow cheaply and allows parties with lots of spare cash to earn a small return without much risk due to the collateral. The repo market is also important for central banks to conduct monetary policies.

Modern repo traders mostly communicate on centralized communication tools to negotiate terms/interest rates and then convert them into executable contracts. This whole process contains a lot of negotiations and routines that were only performed by humans, who are often under stress and need to work around the clock, due to the urgency of the business. The newest advances of AI research provided us modern tools not only to understand natural language, but also can generate natural language with given intention, while at the same time, forecasting the change of interest rates probabilistically, facilitating subsequent optimal trading strategies. Ant Group, as the leader of FinTech industry, with the collaboration between the repo trading desk of MYBank and the AI groups, has automated the whole process, including forecasting, language understanding/generation, contract/execution automation, risk analysis, etc. This ground-breaking system freed up the repo traders from the burden of negotiations around the clock, and largely reduced the potential risk of human errors. At the same time, the fully automated system can boost trading profits by enabling refined fund management and opens up the possibility to apply neural network-based trading strategies. Our system has gone beyond serving just the repo desk of MYBank, and is now helping the modernization of our financial partners on repo trading.