Discussion Initiated About U.S. Hedge Fund Launch

BSQ Research has opened discussions with a senior hedge fund manager and investment consultant in California to launch a macro hedge fund that will invest in sector ETFs using techniques developed jointly by BSQR and a Boston-based financial researcher.

Research Paper About Bankruptcy Prediction to be Published in Data Science for Finance and Economics

Dr Debashis Guha’s paper, based on research carried out in collaboration with Prof Aditya Narvekar of S P Jain School of Global Management’s Sydney campus, has been accepted for publication by the well-known journal Data Science for Finance and Economics.

This research is part of Aditya Narvekar’s doctoral thesis, which has been supervised by Dr Guha, and it studies the use of Machine Learning to forecast corporate bankruptcies.

Research Paper About Sector Rotation to be Published in Journal of Portfolio Management

Dr Debashis Guha’s research paper on AI-based sector rotation, written jointly with Larry Pohlman of Adaptive Investment Solutions, and students at S P Jain School of Global Management, has been accepted for publication at the prestigious Journal of Portfolio Management.

This research was carried out in 2020 and it shows that machine learning method called “Hidden Markov Model” can identify periods of stress in market sectors and this information can be used to construct profitable portfolios.

BSQ Research Approached By Investor for Creating New Crypto Fund

A Mauritius-based investor has approached BSQ Research to explore the possibility of creating a crypto hedge fund that will be acceptable to mainstream investors. Mainstream investors such as institutions and family offices usually shy away from crypto investments because of their extreme volatility and downside. In order to attract these investor, it will be necessary to create a crypto portfolio that has much lower volatility than individual coins, but still earns close to the triple-digit returns that investors expect from crypto.

BSQ Research will carry out an initial study of the feasibility of constructing such a portfolio, possibly using Deep Learning techniques.

Study Shows AI Can Identify High Risk Periods for Equities and Sectors and Enhance Portfolio Performance

Research carried out by Dr Debashis Guha, in collaboration with Dr Lawrence Pohlman of Adaptive Investment Solutions and with the assistance of students from the S P Jain School of Global Management, shows that a machine learning method called Hidden Markov Modelling can identify periods during which the aggregate equity market or some of its sectors exhibit high volatility. Since high-volatility regimes are often associated with bear markets, this methodology can be used to construct tactical portfolios that earn higher returns than the aggregate market.

These results have been submitted for publication.