Summary

Graduate robotics engineer with business training and work experience across autonomous systems, industrial automation, and deep tech R&D. Brings six years of self-directed experience in capital and derivatives markets. Applies quant-based ML methodologies across capital markets.

Tools: Python, C++, pandas, Excel, MATLAB, SQL, NumPy, PyTorch, TensorFlow, PowerPoint

Sector Expertise: Robotics, Automation, AI Infrastructure, Agritech, and Advanced Manufacturing

PROJECTS

Dynamic Factor Portfolio Adjustment using Ridge Regression

I developed a machine learning portfolio framework that studies how different investment factors perform under changing market conditions. It uses historical stock prices to calculate momentum, short term reversal, and low volatility signals. The project measures how well each factor predicted future stock returns and uses a Ridge regression model to estimate which factors may perform better next month. These predictions are converted into changing factor weights and combined to rank individual stocks. The highest ranked stocks form a portfolio, which is then tested using returns, transaction costs, turnover, Sharpe ratio, Sortino ratio, drawdown, and out of sample prediction accuracy.

Monte Carlo Portfolio Simulation for U.S. Small-Cap Stocks

PERSONAL FINANCE EXPLAINERS

BUSINESS REPORTS