Applying Python in Portfolio Optimization

Abstract

Portfolio optimization is one of the core issues in modern finance. It maximizes investment returns while mitigating risks by arranging asset weights rationally. Portfolio optimization not only has important theoretical value but also has a wide range of applications in practice. The goal of this thesis is to compare different portfolio optimization strategies and determine the best portfolio optimization method. This study randomly selected 100 stocks from the S&P 500 index and collected the adjusted closing price data of these stocks on each trading day between January 1, 2019, and January 1, 2025. Stock price data are divided into two parts, including the in-sample period and the out-of-sample period. After a thorough comparison, investors seeking long-term, consistent growth and manageable risk might consider Naive strategy. Because it has the highest return and risk-adjusted return in the selected period and dataset. The Naive strategy achieves the simplest diversification and prevents excessive allocation to individual assets.