Skip directly to content

Reinforcement Learning and Hidden Markov Model Based Smart Trading Strategies

Speaker: Samit Ahlawat

CQF Institute is proud to bring you a free online talk with Samit Ahlawat on Reinforcement Learning and Hidden Markov Model Based Smart Trading Strategies 

Event Agenda 

17:30 - 18:00 BST - Networking and CQF Booth 

18:00 - 19:30 BST - CQF Institute Talk: Samit Ahlawat

19:30 - 20:00 BST - Networking and CQF Booth 

This event can earn you up to 2 CPD credits.

Abstract

Trading strategy design has long been dominated by the use of static rules. Moving-average crossover, momentum-based long-short portfolio trading and buy-and-hold are three most ubiquitous trading strategies. Moving-average crossover-based trading strategy is widely used in equity, fixed income, and currency markets, and has long been regarded as a cornerstone of technical analysis and a building-block for more advanced strategies. Momentum based long-short strategy has been used to demonstrate the presence of momentum effect in security prices, while the buy-and-hold strategy has been frequently used to demonstrate the effectiveness of passive trading strategies. Increasing sophistication of AI algorithms has opened the possibility of algorithms replacing human judgement in portfolio management -- not just over short periods but over longer holding periods.

In this talk, Samit will describe two methodologies of building smart trading strategies: one based on hidden Markov Models and another based on reinforcement learning to address the myopic focus of static rule-based trading strategies.

Speaker's Bio

Samit Ahlawat is a Senior Vice President in Quantitative Research, Capital Modeling at J.P. Morgan Chase in New York. In his current role, he is responsible for building trading strategies for Asset Management and for building risk management models for wholesale credit regulatory risk, as mandated by CCAR and DFAST regulatory exercises. He also works on risk management of credit derivatives, interest rate derivatives and on fixed-income research. His research interests include artificial intelligence, risk management and algorithmic trading strategies. He has a Master’s Degree specializing in numerical computation from the University of Illinois, Urbana-Champaign.