I build Python pipelines with Pandas and NumPy to download, clean and transform financial time series. I implement technical indicators, entry/exit logic and backtesting with realistic costs. Each strategy is evaluated with risk-adjusted metrics and visualized through equity curves and return distributions.
Problem, stack and result
Problem solved
Personal financial research project: I develop algorithmic strategies in Python and evaluate technical indicators with risk-adjusted metrics such as Sharpe, Sortino and max drawdown.
Technologies used
Core stack: Python, Pandas, NumPy. Project technologies: Python, Pandas, NumPy, Matplotlib, Jupyter, Quant Finance.
What I did
My role was Independent researcher. I worked on the technical implementation, product approach and enough documentation for the result to be explained and evolved.
Result or learning
Backtesting with realistic costs, slippage and commissions. Metrics: Sharpe, Sortino, Calmar, max drawdown and beta.
Highlights
- Backtesting with realistic costs, slippage and commissions.
- Metrics: Sharpe, Sortino, Calmar, max drawdown and beta.
- Robustness focus with walk-forward and Monte Carlo analysis.
- Documented in reproducible Jupyter notebooks.