Optimize NYSE, AMEX, and NASDAQ stock portfolios using Genetic Algorithms, mapping characteristics to expected returns, creating value-weighted long-short deciles, rebalancing monthly, and validating with out-of-sample testing.
ASSET CLASS: stocks | REGION: United States | FREQUENCY:
Monthly | MARKET: equities | KEYWORD: Genetic Programming
I. STRATEGY IN A NUTSHELL
Use a Genetic Algorithm to map stock characteristics—momentum, reversals, and moving averages—to expected returns. Go long on the top decile and short the bottom, value-weighted and rebalanced monthly.
II. ECONOMIC RATIONALE
The algorithm identifies non-linear relationships and optimal variable combinations, predicting returns accurately to generate abnormal profits. Its robustness extends across markets and indicator types, demonstrating adaptability and strong Sharpe ratio performance.
III. SOURCE PAPER
Maximizing the Sharpe Ratio: A Genetic Programming Approach [Click to Open PDF]
Yang Liu, Guofu Zhou, Yingzi Zhu, Hunan University – College of Finance and Statistics; Washington University in St. Louis – John M. Olin Business School; Tsinghua University – School of Economics & Management
<Abstract>
While existing studies focus on minimizing model fitting errors, we maximize directly the Sharpe ratio of spread portfolios with a genetic programming (GP) approach. We find that the GP approach can double the performance in the US and outperform internationally, compared with other approaches under examination. We also apply the GP to maximize the Sharpe ratio of investing in all the underlying stocks, which amounts to searching for the stochastic discount factor that prices all the assets. We find that the Sharpe ratio is almost 70% greater than before, indicating the loss of relying on spread portfolios for investing and pricing can be substantial.
IV. BACKTEST PERFORMANCE
| Annualised Return | 8.99% |
| Volatility | 11.29% |
| Beta | N/A |
| Sharpe Ratio | 0.77 |
| Sortino Ratio | N/A |
| Maximum Drawdown | N/A |
| Win Rate | N/A |
