AI for Finance

Apply AI into finance. Develop advanced machine learning models and libraries for financial applications.

AI massively reduces the cost of prediction, while cheap prediction is directly applicable to finance and envisioned to have a huge impact.

We apply algorithms and softwares developped in AI, including OpenAI, TensorFlow, PyTorch, Keras; LSTM, DQN, DDPG, PPO, A2C, SAC, etc., to quantitative trading.

We also design deep learning and deep reinforcement learning (DRL) algorithms, e.g., quantum tensor networks, quantum reinforcement learning, etc.  Exploiting the notion of differential privacy, we build more robust models or ensemble strategies;  We develop a deep reinforcement learning library FinRL for finance.

Scholar data and ESG data as alternative data, we propose a practical machine learning approach and develop trading strategy to capture the scholar data or ESG data driven alpha.

Machine Learning

Machine learning (ML) is the scientific study of algorithms and statistical models that computer systems use to perform a specific task without using explicit instructions, relying on patterns and inference instead. It is seen as a subset of artificial intelligence. The three basic machine learning paradigms are supervised learning, unsupervised learning, and reinforcement learning.

Reinforcement Learning

Reinforcement learning is an area of machine learning concerned with how software agents ought to take actions in an environment in order to maximize the notion of cumulative reward.

Alternative Data

Currently, we study two kinds of alternative data sets: scholar data and ESG data.

Robust Machine Learning Models

We exploit the notion of differential privacy to build more robust machine learning models.

AI4Finance Team

Some highlights
  • Xiao-Yang Liu was invited to talk at SEC, June 2019 [PDF]

  • Over 10 publications on AI in Finance
  • Christina Dan Wang, Assistant Professor of Finance, NYU Shanghai; Global Network Assistant Professor, NYU.
  • Zihan Ding wrote a [Book] Deep Reinforcement Learning: Foundamentals, Research and Applications, 2020, [Link], [RL Tutorial] [RL Zoo]
  • Xiao-Yang Liu wrote 2 chapters for [Book] Reinforcement learning for cyber-physical systems: with cybersecurity case studies. Chapman & Hall/CRC, 2019, [Link].

  • Hongyang Yang, Research Scientist on AI4Finance, 03/01/2020~ present. Master, Department of Statistics, Columbia University, 2016.09~2017.12.
    Data Scientist at Gloabl AI, 2017.03~2018.07. Data Scientist at Credit Suisse (in Wall Street), 2018.07~2019.03. Senior Data Scientist at Moody’s Analytics, 2019.03~2020.03.
  • Yunzhe Fang, Master, Industrial Engineering and Operations Research, Columbia University, 2016.09~2018.06. Research Analyst, Active Equity at BlackRock, now.
  • Wenhang Bao, Master, Department of Statistics, Columbia University, 2016.09~2017.12.  Now, Senior Consultant/Data Scientist at Capgemini.
  • Xinyi Li, Master, Department of Statistics, Columbia University, 2018.9~2019.06. Data Scientist, Feizai Co. Ltd., 2019.07~
  • Runjia Luna Zhang, Bachelor, Electrical Engineering, Columbia University, 2018.9~2019.08. Riken Lab, 2019.09~2020.08.

Publications (Github Codes)

[ICAIF] Hongyang Yang, Xiao-Yang Liu, S. Zhong, A. Walid, Deep reinforcement learning for automated stock trading: an ensemble strategy. ACM International Conference on AI in Finance,  2020. [PDF]
[ICAIF] Q. Chen, Xiao-Yang Liu, Quantifying ESG alpha using scholar big data: An automated machine learning approach. ACM International Conference on AI in Finance, 2020. [PDF]
[BigData] Y. Fang, Xiao-Yang Liu, Hongyang Yang, Practical machine learning approach to capture the scholar data driven alpha in AI industry. IEEE BigData 2019. [PDF]  (AI Publications as Finance Alternative Data).
[ICML Workshop] X. Li, Y. Li, Y. Zhan, Xiao-Yang Liu, Optimistic Bull or Pessimistic Bear: adaptive deep reinforcement learning for stock portfolio allocation. ICML Workshop on Applications and Infrastructure for Multi-Agent Learning, 2019. [PDF]

[ICML Workshop] W. Bao, Xiao-Yang Liu, Multi-agent reinforcement learning for liquidation strategy analysis. ICML Workshop on Applications and Infrastructure for Multi-Agent Learning, 2019. [PDF]

[NeurIPS Workshop] X. Li, Y. Li, Hongyang Yang, L. Yang, Xiao-Yang Liu. DP-LSTM: Differential privacy-inspired LSTM for stock prediction using financial news. Robust ML DP LSTM Financial News, NeurIPS 2019. [PDF]

[NeurIPS Workshop] Z. Xiong, Xiao-Yang Liu, S. Zhong, Hongyang Yang, A. Walid. Practical deep reinforcement learning approach for stock trading. NeurIPS Workshop on Challenges and Opportunities for AI in Financial Services: the Impact of Fairness, Explainability, Accuracy, and Privacy, 2018. [PDF] and [Poster]

[NeurIPS Workshop] W. Lu, Xiao-Yang Liu, Q. Wu, Y. Sun, A. Walid. Transform-based multilinear dynamical system for tensor time series analysis. NeurIPS Workshop on Modeling and Decision-Making in the Spatiotemporal Domain, 2018. [PDF] and [Poster]

[KDD Workshop] X. Li, Y. Li, Xiao-Yang Liu, C. Wang, Risk management via anomaly circumvent: Mnemonic deep learning for midterm stock prediction. KDD Workshop on Anomaly Detection in Finance, 2019. [PDF]

[URTC] R. Zhang, Z. Huang, Xiao-Yang Liu, Machine learning approach for art market. MIT URTC 2019. [PDF]

[EdgeBlock] L. Yang, Xiao-Yang Liu, W. Gong, Secure smart home systems: A blockchain perspective. IEEE INFOCOM Workshop on International Symposium on Edge Computing Security and Blockchain (EdgeBlock), 2020.

[EdgeCom] L. Yang, Xiao-Yang Liu, J. S. Kim, Cloud-based livestock monitoring system using  RFID and blockchain technology. IEEE EdgeCom 2020.

[SmartBlock] L. Yang, Xiao-Yang Liu, X. Li, and Y. Li, Price prediction of cryptocurrency: An empirical study. Springer SmartBlock 2019. [PDF]

[TrustCom] Hongyang Yang, Xiao-Yang Liu, Q. Wu. A practical machine learning approach for dynamic stock recommendation. IEEE TrustCom, 2018. [PDF]

Reach the top ending AI science!

A young team, professional in tensor and deep learning technology, commits to creating top AI algorithms and solutions for cooperates, labs, and communities.