Adaptive Mutation-Enhanced Random Forests for Predictive Modeling in Volatile Financial Markets

Volatile financial markets present a critical challenge for predictive modeling, as rapid price fluctuations, non-stationarity, and high noise levels often reduce the accuracy of traditional machine learning methods. Conventional ensemble approaches, including Random Forests, provide robustness against overfitting but struggle with adaptability to dynamic shifts in market conditions. To address these limitations, this study introduces the Adaptive Mutation-Enhanced Random Forest (AMERF) model, which integrates an evolutionary mutation mechanism into the tree construction process. By dynamically mutating feature subsets and decision thresholds during training, AMERF improves model diversity and adaptability to sudden market transitions. Experiments were conducted using historical stock price and technical indicator datasets from the S&P 500 and NASDAQ indices, covering highly volatile periods such as financial crises and pandemic-induced fluctuations. Data preprocessing included normalization, rolling-window feature engineering, and volatility-based segmentation to enhance temporal dependencies. Comparative evaluation against baseline Random Forests, Gradient Boosting, and LSTM models demonstrated that AMERF achieved superior performance, yielding improvements of up to 7% in predictive accuracy, with notable gains in F1-score, precision, and Sharpe ratio optimization. The primary contributions include: (1) introducing a mutation-driven adaptation strategy for ensemble models in finance, (2) demonstrating robustness across extreme volatility regimes, and (3) providing evidence of practical applicability in algorithmic trading and risk management. This research highlights the potential of evolutionary ensemble learning to bridge the gap between static models and dynamic financial realities. Future work will explore hybrid deep learning–mutation ensembles for real-time predictive trading systems.