Post

Time-Series Modeling on Monthly Returns and Trading Strategies with 6 Portfolios


FMA4200 Final Project: Time Series Modeling for Financial Data

Time-Series Modeling on Monthly Returns and Trading Strategies with 6 Portfolios

The project modeled data distribution and explored arbitrage strategies by implementing fundamental time-series analysis.

The paper also introduced optimal mean-variance method to lower the volatility of each portfolio, and made comparison between the classical algorithm and its variant:

  • Least mean-variance algorithm
  • Black-Litterman algorithm

Results:

  • Prior knowledge (investors’ options, market equilibrium, etc.) brings in extra information (alpha enhancement)
  • Lower risk penalty coefficient can improve annualized returns

This post is licensed under CC BY 4.0 by the author.