Wavelet Denoising and Model Parsimony in High-Frequency Momentum Strategies: Evidence from China’s ChiNext Market

This study introduces a sophisticated dual-denoising framework for high-frequency momentum strategies in China's ChiNext market, integrating wavelet-based temporal filtering with isolation forest cross-sectional anomaly detection. Utilizing a comprehensive dataset of over 2 million daily observations from January 2016 to November 2025, the results demonstrate that wavelet denoising achieves exceptional efficacy for turnover series with a mean Signal-to-Noise Ratio improvement of 10.7 dB, while isolation forest robustly identifies anomalous stocks characterized by excessive trading activity and distorted risk-return profiles. Empirical results reveal that linear models with wavelet denoising consistently outperform complex alternatives, with Support Vector Machines achieving Sharpe ratios of 0.1132 in long portfolios and 0.0649 in long-short implementations. Contrary to conventional wisdom, simpler architectures demonstrate superior performance, with single-layer neural networks and regularized linear models surpassing deeper architectures across all denoising configurations. The methodology demonstrates remarkable regime invariance, maintaining consistent performance during both low-volatility and high-volatility market states. These findings establish wavelet denoising as a critical preprocessing technique for high-frequency financial data and challenge assumptions about the necessity of complex models in quantitative finance, providing computationally efficient approaches suitable for both institutional and retail investors.