Systematic Algorithmic Trading
Strategies
Developed by: Saudeep
Chattopadhyay
Date: October 2024
Problem Statement
• The objective of this project is to develop and
implement systematic, algorithmic trading
strategies for the Nifty 50 index stocks. These
strategies are built around technical indicators
and backtesting techniques, using historical
data to optimize returns and mitigate risks.
Work Approach
• 1. Data Collection: Historical price data for
Nifty 50 stocks using yfinance API.
• 2. Trading Strategy Implementation: Moving
average crossover strategy using a 50-day and
200-day moving average.
• 3. Performance Evaluation: Calculated metrics
like CAGR, Sharpe Ratio, Sortino Ratio, and
Max Drawdown.
• 4. Backtesting: Evaluated the strategy's
Datasets & Tools
• Datasets: Historical price data for Nifty 50
stocks (2000-2024).
• Tools & Libraries: yfinance, pandas, numpy,
matplotlib.
• Development Environment: Google Colab.
Trading Strategy Implementation
• A moving average crossover strategy was
used, with the following parameters:
• - Short Window: 50-day moving average.
• - Long Window: 200-day moving average.
• Buy signals were generated when the short-
term moving average crossed above the long-
term average, and sell signals were generated
for the opposite.
Backtesting Framework
• Backtesting was performed to evaluate the
trading strategy over historical data.
• Metrics recorded included buy/sell signals,
trade profitability, and risk metrics.
Performance Metrics
• 1. CAGR: 64.42%
• 2. Sharpe Ratio: 1.36
• 3. Sortino Ratio: 4.20e
• 4. Maximum Drawdown: -92.38%
• 5. Total Portfolio Return: 54,972.70
Monte Carlo Simulation
• Monte Carlo simulation was used to simulate
portfolio returns under different market
conditions.
• 1,000 runs were performed, and the
cumulative returns were plotted to assess risk-
adjusted performance.
Results Summary
• The strategy yielded a total return of
54,972.70 with a CAGR of 64.42%.
• Risk metrics such as Sharpe and Sortino ratios
indicated strong risk-adjusted performance.
• However, maximum drawdown was
significant, highlighting potential areas for
improvement in risk management.
Conclusion & Future
Improvements
• The systematic trading strategy performed
well in terms of returns, but risk management
needs improvement.
• Future work could focus on optimizing stop-
loss thresholds and diversifying strategies to
minimize drawdowns.
