We develop a deep-visualization framework for timing the factor zoo. Historical factor return trajectories are converted to two complementary image representations, which are then learned by convolutional neural networks (CNNs) to generate factor-specific timing signals. Using 206 equity factors, our CNN-based forecasts deliver significant economic gains: timed factors earn an average annualized alpha of about 6\%, and a high-minus-low strategy yields an annualized Sharpe ratio of 1.22. The outperformance is robust to transaction costs, post-publication decay, and factor category-level analysis. Interpretability analyses reveal that CNNs extract predictive signals from path boundaries and regime shifts, capturing patterns orthogonal to investor attention.

This study investigates the effectiveness of the volatility-timing strategy in the Chinese equity market. We find that the volatility-managed portfolio (VMP) consistently outperforms its original counterpart, both in individual factor analysis and mean-variance efficient multifactor assessment, and the results are robust in outof-sample setup. Notably, the outperformance is mostly driven by stocks with high arbitrage risk, short-selling constraints, relatively smaller size, and lottery preferences. Further, the multifactor portfolio constructed from the volatility-managed strategy outperforms other portfolios especially in turmoil periods such as high sentiment and low macroeconomic confidence periods. Our findings suggest that in the Chinese equity market with typical trading frictions, volatility timing strategies consistently gain profitable performance.