Commodity Multi-Asset Strategy Python Project

This school project implements a basic quantitative analysis of historical commodity prices and constructs a multi-asset strategy optimization. The code demonstrates data acquisition, technical indicator computation, visualization, and a simple strategy backtest using randomly generated portfolio weights.

---

Project Summary

• Aim: Analyze historical price data for major commodities and build a random-weighted strategy index to maximize portfolio value over the past 10 years.
• Instruments Covered:
  • Crude Oil (CL=F)
  • Gold (GC=F)
  • Silver (SI=F)
  • Copper (HG=F)
  • Wheat (ZW=F)
• Techniques Demonstrated: Data retrieval, price visualization, moving averages, Bollinger Bands, Relative Strength Index (RSI), random portfolio construction, and strategy index optimization.

---

Project Structure

1. Data Acquisition:
   Download 10 years of daily adjusted close prices for chosen commodities using the Yahoo Finance API (yfinance).
2. Visualization and Analysis:
   • Plot raw historical price data.
   • Compute and plot 50-day simple moving averages (SMA).
   • Calculate and visualize Bollinger Bands.
   • Compute and display the RSI (Relative Strength Index) for trend analysis.
3. Strategy Simulation:
   • Generate 100 random combinations of asset weights (using Dirichlet distribution).
   • Compute the performance index of strategies rebalancing daily by these weights.
   • Select and display the best-performing strategy and its weights.

---

Key Features

• Python Libraries: yfinance, pandas, matplotlib, numpy, dateutil
• Technical Indicators: SMA, RSI, Bollinger Bands
• Portfolio Construction: Daily rebalancing, random portfolio simulation, index tracking
• Visualization: Matplotlib-based, with clear legends and axis labels