Direct linear regression prediction of index returns has long been recognized as a challenging task in industry time-series timing research. Constrained by the extremely low signal-to-noise ratio and pervasive nonlinear characteristics of financial data, ordinary least squares (OLS) regression suffers from poor out-of-sample performance and hardly outperforms the historical average benchmark. Although academia has proposed a nonlinear prediction framework based on sign-magnitude decomposition and Copula function dependence coupling, the selection and estimation of Copula families introduce substantial model uncertainty in practical multi-factor timing implementations. Against this backdrop, this study draws on the core framework published in the Journal of Banking and Finance, constructing a concise, logically consistent nonlinear return prediction framework by conditioning return signs (ups and downs directions) on contemporaneous magnitude (volatility states), while eliminating complex Copula dependence modeling. Based on the Conditioning Sign on Magnitude (CSM) method, this paper elaborates the model construction logic, econometric advantages, and empirical performance. Empirical tests based on 74-year monthly excess return data of the S&P 500 index verify that the CSM framework achieves superior out-of-sample statistical accuracy and economic utility with low implementation costs. It effectively overcomes the inherent limitations of linear models and the parameter instability of Copula-based methods, providing a lightweight and efficient optimization scheme for medium- and low-frequency time-series quantitative timing.
Weijian Huang, Yuanqi Huang, Xianpeng Jiang· Journal of the European Acad...· 0 citations
In the field of high-frequency quantitative trading for cryptocurrencies, the industry has long fallen into an algorithm arms race centered on deep learning models such as LSTM and Transformer. Researchers excessively pursue marginal improvements in predictive indicators including Mean Squared Error (MSE) and Directional Accuracy, which leads to a widespread dilemma: high prediction accuracy accompanied by poor live trading performance. Taking hourly high-frequency trading of Bitcoin as the research object, this paper constructs a comprehensive transaction cost system covering explicit handling fees, bid-ask spreads and slippage. Adopting the Walk-Forward dynamic backtesting framework, this study systematically compares the performance of traditional time series models, complex deep learning models and transaction cost-aware filtering strategies. The empirical results show that: first, there is a significant disconnect between model prediction accuracy and actual net returns; marginal improvements in prediction brought by complex models cannot offset profit losses caused by transaction frictions in high-frequency trading. Second, simple signal filtering rules designed based on transaction costs deliver far better profitability improvements than iterative optimization of deep learning architectures. Third, although the target strategies achieve impressive returns in single-path backtesting, their returns are extremely unevenly distributed across time intervals with weak statistical significance, indicating prominent stability risks in live trading. The conclusions of this research provide theoretical basis and practical references for the R&D of cryptocurrency quantitative strategies, the construction of standardized backtesting systems and live trading risk control.
Weijian Huang, Zhanwei Wang, Wenchang Jiang· Journal of the European Acad...· 0 citations
Current machine learning-based quantitative high-frequency trading suffers from a significant Prediction-to-Trading Gap. Academic and industrial research overly focuses on the optimization of model prediction errors while ignoring the devastating impact of real-market trading frictions on strategy returns. Taking the hourly high-frequency trading of BTC/USDT perpetual contracts as the research scenario, this paper constructs a quantitative trading system covering three heterogeneous time-series models (XGBoost, LSTM, and iTransformer) under the constraint of 10 bps full-dimensional transaction costs. A Cost-Aware Execution Filter (CA) is introduced, combined with the 27-fold non-anchored Walk-Forward Optimization (WFO) framework and a three-layer nested feature engineering system for empirical research. The results show that all three machine learning models can achieve excess returns in the frictionless scenario, with the annualized return of iTransformer reaching 181.76%. However, when 10 bps real trading frictions are introduced, all naive unfiltered strategies incur comprehensive losses, with annualized returns collapsing ranging from -64.00% to -98.00%. The CA filtering mechanism substantially reduces the strategy turnover rate by two orders of magnitude and effectively repairs strategy returns. The optimal strategy achieves an annualized return of 65.40% with a Sharpe ratio of 1.09. The empirical results verify that the core bottleneck of high-frequency quantitative trading is not model prediction accuracy but the cost adaptation mechanism of signal transformation, and a simple and efficient transaction cost filtering strategy is far more valuable than blindly iterating complex time-series models. This study provides an important reference for the research and development, real-market implementation, and standardized backtesting system construction of cryptocurrency high-frequency quantitative strategies.
Weijian Huang, Zhanwei Wang, Xianpeng Jiang· Journal of the European Acad...· 0 citations