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 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.

It is diffffcult to understand the risk-return trade-off in option market with observable factormodels. In this paper, we employ a latent factor model for delta-hedge option returns over a varietyof important exchange traded options in China, based on the instrumented principal componentanalysis (IPCA). This model incorporates conditional betas instrumented by option characteristics,to tackle the diffffculty caused by short lifespans and rapidly migrating characteristics of options. Ourresults show that a three-factor IPCA model can explain 19.30% variance in returns of individualoptions and 99.23% for managed portfolios. An asset pricing test with bootstrap shows that there isno unexplained alpha term with such a model. Comparison with observable factor model indicatesthe necessity of including characteristics. We also provide subsample analysis and characteristicimportance.

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.

The general financial theory predicts a carbon premium, as brown stocks bear greater uncertainty under climate transition. However, a contrary green premium has been identified in China, as evidenced by the return spread between green and brown sectors. The aggregated climate transition sentiment, measured from news data using a large language model, explains 12%-33% of the variability in the anomalous alpha. This factor intensifies after China announced its national commitments. The sentiment-driven green premium is attributed to speculative trading by retail investors targeting green “concept stocks.” Additionally, the discussion highlights the advantages of large language models over lexicon-based sentiment analysis.

We examine the performance of actively managed Chinese mutual Funds over the period 2002-2020. Using the bootstrap-based false discovery technique, we find that 19.25% of Chinese actively managed mutual funds produce positive-alpha, which contrasts with existing studies documented by others in developed markets. Our findings survive a battery of robustness tests. Unlike in developed markets, equilibrium accounting may not hold in China as the Chinese stock market is dominated by retail investors instead of mutual funds, and thus the mutual funds in China can be more skilled at the expense of the retail investors. We find supportive evidence of the applicability of the bootstrap-based false discovery rate method by conducting simulations.

Exploiting ffnancial news stories data, we construct news-implied linkages and document a strong lead-lag effect of ffrms with shared news coverage in China’s stockmarket. The news-link momentum strategy generates a monthly return of 1.33% and a four-factor alpha (Liu et al., 2019) of 1.43%. While prior evidence on the attention dynamics among ffrms with joint news coverage is limited, we show that the momentum spillover of news-linked ffrms is largely driven by investor underreaction. The return predictability from news links is also robust to controlling for alternative economic linkages. The ffndings suggest that information diffuses sluggishly among news-connected ffrms, thereby providing new evidence on the implication of media coverage for pricing efffciency.

Research into asset pricing anomalies in the China A-share market is hampered given the short time series of available returns. Even when average excess returns on candidate factor portfolios are economically sizeable, conventional portfolio sorting methods lack statistical power. We apply an efficient sorting procedure that combines firm characteristics with the covariance matrix. For the China A-share market, we find that the efficient sorting procedure doubles the t-statistics compared to conventional portfolio sorts, leading to nine instead of three significant anomalies over the postreform period from 2008 to 2020. We find significant size, value, low-risk, and returns-based anomalies. While portfolio characteristics differ between sorting methods, we find that efficient sorting portfolios highly correlate with equally weighted portfolios and capture the same underlying anomaly.

We examine the information content of changes in shareholdings after private issuance of public equity (PIPE) by mutual funds that participate in PIPEs in China. The results show that the changes in shareholdings is positively related to alpha and cumulative abnormal return (CAR) for PIPE issuers with high information asymmetry, suggesting that the participating mutual funds have superior information. These results are robust after controlling for investment skill, geographic location, and alumni relation. The positive relation between shareholding change and information content is driven by PIPE issuers with weaker corporate governance. In addition, the positive relation is stronger when the placement discount is lower. These results are consistent with a hypothesis that controlling shareholders/management in Chinese PIPE firms may collude with mutual funds to do tunneling.

随着“互联网+”成为国家战略，公募基金行业迎来了爆发性增长，截止到2016年9月底，我国境内共有公募基金管理公司107家，基金总数达到3415支，资产达到8.83万亿元。“互联网+”基金作为新兴事物，既很大程度上推动了基金行业的发展，又为基金行业提供了基于行为金融学理论的新的投资思路。对互联网+基金的绩效评价重要性日益凸显。 运用绝对收益指标和多种风险调整后的收益指标、CAPM单因素模型、Fama-French三因素模型、Carhart四因素模型进行业绩归因分析，重点考察了由大数据因子产生的超额Aalpha情况，并针对实证结果从行为金融学的角度开展分析，在一定程度上填补了目前“互联网+”基金绩效评价的空白。 研究结果表明，2014年6月16日至2016年9月30日，“互联网+”股票型基金的绝对收益率要优于比较组，风险收益和波动率弱于比较组；通过CAPM、Fama-French三因子模型、Carhart四因素模型，超额收益显著优于比较组。同时，基金所依托的不同互联网数据平台，对投资风格也有所影响。