RAPTOR: An AI- and Data-Driven Investment and Risk Management System

Raptor is a research project mining diverse alphas in stock markets. Alphas are stock prediction models capturing complex trading signals.

Raptor focus on two research directions:

  • In the first direction, we design novel deep learning models as alphas to increase the prediction accuracy.
  • In the second direction, we design an alpha mining framework, AlphaEvolve, to automatically mine formulaic models and recursive models as alphas.

View our Raptor publication on the ACM Special Interest Group on Management of Data (SIGMOD) 2021:

AlphaEvolve: A Learning Framework to Discover Novel Alphas in Quantitative Investment [ paper link]

Alpha

Steering through complex financial phenomena, we devise various methods to deliver diverse alphas with good performance.

Research Highlights

Unveiling the Power of Multi-Modality in Stock Predictions

A multi-modal model designed for generalized stock prediction, leveraging mutiple sources of information such as stock price, stock news, and implied volatility.

AlphaEvolve

AlphaEvolve is a framework that automatically mines novel alphas with high returns and low correlations with an existing set of alphas.

Stock Prediction With Noise Awareness

This work focuses on reducing the contribution of noisy instances caused by missing sources of information in model inputs.

People

Professors

Avatar

Beng Chin Ooi

Distinguished Professor, Computer Science, School of Computing

Avatar

Huang Ke-Wei

Associate Professor in the Department of Information Systems and Analytics,
Executive Director, Asian Institute of Digital Finance, NUS

Researchers

Avatar

Zhaojing Luo

Research Fellow in the Database Systems Research Group at NUS

Avatar

James Can Cui

PhD Student, NUS School of Computing

Avatar

Benjamin Lee Hong Rui

Final-year Student, NUS School of Computing

Avatar

Kleon Ang

Final-year Student, NUS School of Computing

Contact