• Tested dynamic weighting schemes in a multi-factor setting for model selection in US large cap and Japan
• Implemented, tested and compared multiple natural language processing for sentiment analysis, such as dictionary-based sentiment classification, Naive-Bayes, logistic regression and recursive-neural-network (RNN)
• Created a product by achieving universe selection from global equity list through a natural language processing algorithm (Python) which filtered securities with a specific selection criteria
• Implemented model back-testing through portfolio simulation; applied fundamental and statistical risk models for risk-return attribution
• Constructed a pattern-matching algorithm which matched current factor performance with historical patterns in order to predict similar behavior in the future
• Maintained and updated existing quantitative alpha models for global equity selection across different universes, including but not limited to global, non-US, emerging, European and Asian markets
• Generated quantitative metrics for executives and portfolio managers for various portfolio trading analysis 

•  Currently working at a multi -asset, multi -strategy trading desk, overseeing proprietary capital in Indian market cash and derivatives segment.
•  Specialization in creating trading models based on OHLC data, with focus on high Sharpe ratio and low correlation between models.
•  Core strategies include intraday short only, nifty/banknifty pair trading, sectoral stocks basket trading, currency derivatives pair trading.
•  Developed a customized stock screener in python which screens stocks on the basis of various statistical parameters.