Submit Manuscript
Edit a Special Issue
TY - JOUR AU - Yi, Yingnan AU - Gao, Xue PY - 2025 DA - 2025/12/09 TI - The Application of Dual-Denoised Momentum Factors in Portfolio Management: A Study of ChiNext Stocks for Retail Investors JO - ICCK Journal of Applied Mathematics T2 - ICCK Journal of Applied Mathematics JF - ICCK Journal of Applied Mathematics VL - 1 IS - 3 SP - 129 EP - 144 DO - 10.62762/JAM.2025.721050 UR - https://www.icck.org/article/abs/JAM.2025.721050 KW - momentum investing KW - wavelet denoising KW - portfolio management KW - ChiNext market KW - machine learning KW - financial signal processing AB - Momentum-based investment strategies face persistent challenges from noise contamination in financial time series, particularly within emerging markets such as China's ChiNext board. Traditional enhancement approaches typically address symptoms rather than underlying causes, resulting in continued vulnerability to market regime changes and performance deterioration. This study develops and evaluates a dual-denoising framework that integrates wavelet analysis for temporal noise reduction with isolation forest algorithms for cross-sectional anomaly detection. Our methodology employs comprehensive analysis of 1,200-1,300 ChiNext stocks spanning the 2015-2025 period, utilizing multiple machine learning architectures to assess portfolio performance across both long-only and long-short implementations. Key empirical findings demonstrate that: denoised momentum factors substantially improve predictive accuracy and portfolio performance; wavelet-based temporal denoising achieves remarkable effectiveness for turnover data with mean signal-to-noise ratio improvements of 6.4 dB; isolation forest cross-sectional anomaly detection provides critical risk management benefits by systematically eliminating stocks characterized by excessive trading activity and poor returns; and single-layer neural networks with isolation forest denoising achieve superior performance metrics, including 0.0199 monthly returns and a 0.2189 Sharpe ratio, outperforming more complex architectural alternatives. Addressing noise contamination at the data level represents a more fundamental solution than conventional enhancement techniques for momentum strategy limitations. Our findings establish systematic denoising as an effective approach for enhancing momentum-based investment strategies while maintaining practical implementability, with significant implications for both quantitative portfolio management and retail investor applications in emerging markets. SN - 3068-5656 PB - Institute of Central Computation and Knowledge LA - English ER -
@article{Yi2025The,
author = {Yingnan Yi and Xue Gao},
title = {The Application of Dual-Denoised Momentum Factors in Portfolio Management: A Study of ChiNext Stocks for Retail Investors},
journal = {ICCK Journal of Applied Mathematics},
year = {2025},
volume = {1},
number = {3},
pages = {129-144},
doi = {10.62762/JAM.2025.721050},
url = {https://www.icck.org/article/abs/JAM.2025.721050},
abstract = {Momentum-based investment strategies face persistent challenges from noise contamination in financial time series, particularly within emerging markets such as China's ChiNext board. Traditional enhancement approaches typically address symptoms rather than underlying causes, resulting in continued vulnerability to market regime changes and performance deterioration. This study develops and evaluates a dual-denoising framework that integrates wavelet analysis for temporal noise reduction with isolation forest algorithms for cross-sectional anomaly detection. Our methodology employs comprehensive analysis of 1,200-1,300 ChiNext stocks spanning the 2015-2025 period, utilizing multiple machine learning architectures to assess portfolio performance across both long-only and long-short implementations. Key empirical findings demonstrate that: denoised momentum factors substantially improve predictive accuracy and portfolio performance; wavelet-based temporal denoising achieves remarkable effectiveness for turnover data with mean signal-to-noise ratio improvements of 6.4 dB; isolation forest cross-sectional anomaly detection provides critical risk management benefits by systematically eliminating stocks characterized by excessive trading activity and poor returns; and single-layer neural networks with isolation forest denoising achieve superior performance metrics, including 0.0199 monthly returns and a 0.2189 Sharpe ratio, outperforming more complex architectural alternatives. Addressing noise contamination at the data level represents a more fundamental solution than conventional enhancement techniques for momentum strategy limitations. Our findings establish systematic denoising as an effective approach for enhancing momentum-based investment strategies while maintaining practical implementability, with significant implications for both quantitative portfolio management and retail investor applications in emerging markets.},
keywords = {momentum investing, wavelet denoising, portfolio management, ChiNext market, machine learning, financial signal processing},
issn = {3068-5656},
publisher = {Institute of Central Computation and Knowledge}
}
Copyright © 2025 by the Author(s). Published by Institute of Central Computation and Knowledge. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. 
Portico
All published articles are preserved here permanently:
https://www.portico.org/publishers/icck/