Hirschey, Nicholas H.Schandl, Samuel2024-12-062024-12-062024-01-232023-12-20http://hdl.handle.net/10362/176276The individual project investigates the impact of machine learning, specifically the Random Forest model, on momentum-based stock selection strategies. It evaluates the model's predictive accuracy and compares the performance of strategies based on actual versus predicted returns. Findings reveal that machine learning enhances prediction accuracy and, when applied to momentum strategies, demonstrates reduced volatility, lower drawdowns, and improved risk-adjusted returns. The study highlights the model's resilience, particularly in volatile market conditions, while acknowledging limitations related to data and computational resources. This research offers insights into the integration of machine learning in financial strategies to navigate complex market dynamics.engAsset managementTradingMachine learningStock predictionRandom forestMomentum strategymaster thesis203680979