SWHY(SZ:000166) Shenwan Hongyuan Securities·2025-09-22 09:04Group 1 - The report emphasizes the importance of identifying the current market state, either "trend" or "oscillation," to aid in timing and stock selection strategies [2][6][48] - A two-phase, layered diagnostic algorithm is employed to define the index state, utilizing a "zig-zag" algorithm combined with breakpoint correction for historical performance analysis [2][9][10] - The study constructs six feature variables from price, volume, and volatility dimensions to capture market trend changes and emotional fluctuations, achieving over 80% accuracy in predicting future market states with various machine learning models [2][26][27] Group 2 - The report outlines a dynamic position management strategy based on model predictions, switching between "momentum" logic in trend states and "mean reversion" logic in oscillation states [2][46] - The decision tree model-driven strategy yielded a total return of 77.26% and a Sharpe ratio of 1.12 during the backtesting period from 2020 to 2025, significantly outperforming the buy-and-hold benchmark [2][49][70] - The report highlights the effectiveness of the decision tree model in accurately signaling market states, leading to robust returns and risk management during market downturns [2][46][70]