Artificial Intelligence & Financial Markets
The world of investment is currently undergoing a digital transformation, as interest in the adoption of AI and alternative data sources to generate data-driven investment strategies is at the forefront of many major asset management firms and hedge funds. The questions to ask are: What data sources are relevant? What type of algorithms can be used to extract valuable signals from them? And what is the best overall roadmap to adding value to the investment process?
Prof. Bari initiated a research project to address all of these questions. Together with his team, he developed an algorithmic framework that can help understand the factors that affect business performance, stock prices and earnings. Their framework works by surveying a universe of financial entities and alternative data sources, scoring the validity of the data, and then extracting predictive factors that can be used for either automated or human-controlled investment decisions.
The analytics framework, which consists of both theory and practical algorithms, draws from the most recent advances of several core pillars of computer science, including natural language processing, predictive analytics, knowledge representation and reasoning, and swarm intelligence.
Selected Publications:
Anasse Bari, Pantea Peidaee, Aniruddh Khera, Jianghao Zhu, Hongting Chen. "Predicting financial markets using the wisdom of crowds." In 2019 IEEE 4th International Conference on Big Data Analytics (ICBDA), pp. 334-340. IEEE, 2019.
Rafael Moraes, Anasse Bari, Jiachen Zhu. "Restaurant Health Inspections and Crime Statistics Predict the Real Estate Market in New York City." In International Conference on Machine Learning, Optimization, and Data Science, pp. 543-552. Springer, Cham, 2019.
Anasse Bari, Lihao Liu. “Probing the Wisdom of Apple, Inc., Crowds Using Alternative Data Sources.” In InsideBigData, 2017.
Nicholas Greenquist, Doruk Kilitcioglu, Anasse Bari. "Gkb: A predictive analytics framework to generate online product recommendations." In 2019 IEEE 4th International Conference on Big Data Analytics (ICBDA), pp. 414-419. IEEE, 2019.