We introduce a deep visualization (DV) framework that turns conventional commodity data into images and extracts predictive signals via convolutional feature learning. Specifically, we encode futures price trajectories and the futures surface as images, then derive four deep‑visualization (DV) predictors, carry ($bs_{DV}$), basis momentum ($bm_{DV}$), momentum ($mom_{DV}$), and skewness ($sk_{DV}$), each of which consistently outperforms its traditional formula‑based counterpart in return predictability. By forming long–short portfolios in the top (bottom) quartile of each DV predictor, we build an image‑based four‑factor model that delivers significant alpha and better explains the cross‑section of commodity returns than existing benchmarks. Further evidence shows that the explanatory power of these image‑based factors is strongly linked to macroeconomic uncertainty and geopolitical risk. Our findings reveal that transforming conventional financial data into images and relying solely on image-derived features suffices to construct a sophisticated asset pricing model at least in commodity markets, pioneering the paradigm of image‑based asset pricing.

We leverage machine learning to introduce belief dispersion measures to distinguish different opinion (DO) and information asymmetry (IA). Our measures align with the human-based measure and relate to economic outcomes in a manner consistent with theoretical prediction: DO positively relates to trading volume and negatively linked to bid-ask spread, whereas IA shows the opposite effects. Moreover, IA negatively predicts the cross-section of stock returns, while DO positively predicts returns for underpriced stocks and negatively for overpriced ones. Our findings reconcile conflicting disagree-return relations in the literature and are consistent with Atmaz and Basak (2018)’s model. We also show that the return predictability of DO and IA stems from their unique economic rationales, underscoring that components of disagreement can influence market equilibrium via distinct mechanisms.

We construct a novel risk-based similarity peer network by applying machine learning techniques to extract a comprehensive set of disclosed risk factors from firms' annual reports. We find that a firm's future returns can be significantly predicted by the past returns of its risk-similar peers, even after excluding firms within the same industry. A long-short portfolio, formed based on the returns of these risk-similar peers, generates an alpha of 84 basis points per month. This return predictability is particularly pronounced for negative-return stocks and those with limited investor attention, suggesting that the effect is driven by slow information diffusion across firms with similar risk exposures. Our findings highlight that the risk factors disclosed in 10-K filings contain valuable information that is often overlooked by investors.

I conduct an exploratory study about the feasibility of factor timing in the Chinese stock market, covering 24 representative and well-identiffed risk factors in ten categories from the literature. The long-short portfolio of short-term reversal exhibits strong and statistically signiffcant out-of-sample predictability, which is robust across various models and all types of predictors. However, such results are not evident in the prediction of all other factors’ long-short portfolios, as well as all factors’ long-wing and short-wing portfolios. The high exposure to the market beta, together with the unpredictability of the market return, explains these failures to some degree. On the other hand, a simple investment strategy based on predicted returns of the reversal factor’s long-short portfolio obtains a signiffcant return three times higher than the simple buy-and-hold strategy in the sample period, with a signiffcant annualized 20.4% CH-3 alpha.

This study reconsiders the timing of the equity risk factors by using the flexible neural networks specified for image recognition to determine the timing weights. The performance of each factor is visualized to be standardized price and volatility charts and `learned' by flexible image recognition methods with timing weights as outputs. The performance of all groups of factors can be significantly improved by using these ``deep learning--based'' timing weights. In addition, visualizing the volatility of factors and using deep learning methods to predict volatility can significantly improve the performance of the volatility-managed portfolio for most categories of factors. Our further investigation reveals that the timing success of our method hinges on its ability in identifying ex ante regime switches such as jumps and crashes of the factors and its predictability on future macroeconomic risk.

We develop an information choice model where information costs are sticky and co-move with firm-level intrinsic uncertainty as opposed to temporal variations in uncertainty. Incorporating analysts' forecasts, we predict a negative relationship between information costs and information acquisition, as proxied by the predictability of analysts' forecast biases. Finally, the model shows a contrasting pattern between information acquisition and intrinsic and temporal uncertainty, where intrinsic uncertainty strengthens return predictability of analysts' biases through the information cost channel, while temporal uncertainty weakens it through the information benefit channel. We empirically confirm these opposing relationships that existing theories struggle to explain.

We introduce a novel perspective on private information, specifically microstructure-based private information, to unravel how institutional investors predict stock returns. Using tick-by-tick transaction data from the Chinese stock market, we find that in retail-dominated markets, institutional investors positively predict stock returns, consistent with findings from institution-dominated markets. However, in contrast to the traditional view that institutional investors primarily rely on value-based private information, our results indicate that microstructure-based private information contributes almost as much to their predictive power as value-based private information does, with both components jointly accounting for approximately two-thirds of the total predictive power of institutional order flow. This finding reveals that retail investors’ trading activities significantly impact institutional investors, naturally forcing them to balance firm value information with microstructure information, thus profoundly influencing the price discovery process in the stock market.

This paper improves the expected return variable and the corresponding trend factor documented by Han, Zhou, and Zhu (2016) and reveals the incremental predictability of this novel expected return measure on stock returns in the Chinese stock market. Portfolio analyses and firm-level cross-sectional regressions indicate a significantly positive relation between the improved expected return and future returns. These results are robust to the short-, intermediate-, and long-term price trends and other derived expected returns. Our improved trend factor also outperforms all trend factors constructed by other expected returns. Additionally, we observe that lottery demand, capital states, return synchronicity, investor sentiment and information uncertainty can help explain the superior performance of the improved expected return measure in the Chinese stock market.

Beyond a bias toward local stocks, investors prefer companies in certain cities over others. This study uses the geographic network of investor-followed stocks from stock watchlists to identify intercity investment preferences in China. We measure the city-pair connectivity by its likelihood of sharing an investor in common whose stock watchlist is highly concentrated in the firms of that city pair. We find that a higher connectivity-weighted aggregate stock demand-to-supply ratio across connected cities is associated with higher stock valuations, higher turnover, better liquidity, and lower cost of equity for firms in the focal city. The effects are robust to controls for geographic proximity and the broad investor base, are stronger among small firms, extend to stock return predictability, and imply excess intercity return comovement. Our results suggest that city connectivity revealed on the stock watchlist helps identify network factors in asset pricing.

Prior literature shows that implied volatility spreads between call and put options are positively related to future underlying stock returns. In this paper, however, we demon- strate that the volatility spreads are negatively related to future out-of-the-money call option returns. Using unique data on option volumes, we reconcile the two pieces of evidence by showing that option demand by sophisticated, firm investors drives the posi- tive stock return predictability based on volatility spreads, while demand by less sophis- ticated, customer investors drives the negative call option return predictability. Overall, our evidence suggests that volatility spreads contain information about both firm funda- mentals and option mispricing.