Predictability

  • 详情 The "Clear but Neglected" Premium: Explaining Industry Heterogeneity in Fundamental Return Predictability
    Using Chinese A-share stocks from 2007–2021, we study whether and why the return-predictive power of accounting-based fundamental signals varies systematically across industries. We construct a high-dimensional set of 101 financial indicators and estimate industry-specific forecasting models (OLS, Ridge, Lasso, Elastic Net) on within-industry standardized ratios. Predictability is strongly heterogeneous: fundamentals forecast returns reliably in traditional, manufacturing-intensive sectors (Industrials, Utilities, Consumer Discretionary, and Real Estate), but are weak or absent in high-attention “glamour” sectors (Information Technology, Healthcare, Energy, Materials, and Consumer Staples). To explain this pattern, we implement a mediated-moderation framework that links cross-industry differences in the fundamentals–return relation to (i) earnings uncertainty, (ii) investor attention, and (iii) limits to arbitrage. The evidence supports a dual-channel mechanism: fundamental strategies perform best when accounting signals are clear (low earnings uncertainty) yet neglected (limited attention), consistent with stable accounting information being incorporated into prices more slowly in those sectors. By contrast, limits to arbitrage do not explain the industry differences. Overall, our findings suggest that industry heterogeneity in fundamentals-based predictability reflects the interaction between information quality and investor attention rather than primarily trading-friction explanations.
  • 详情 Multi‑Source Heterogeneous Data Fusion and Stock Market Predictability: Evidence from Chinese Investor Sentiment and Market Indicators
    Investor sentiment constitutes a pivotal nonrational determinant of asset pricing within capital markets. Nevertheless, achieving high-precision sentiment analysis regarding Chinese financial short texts and effectively integrating these metrics into predictive modeling remains a formidable challenge. Focusing on Vanke A within the Chinese A-share market, this study proposes a quantitative framework for investor sentiment analysis that amalgamates textual commentary from the East Money Guba forum with high-frequency trading data from CSMAR, leveraging a hybrid architecture of BERT deep learning and CatBoost regression. By meticulously constructing a high-fidelity annotated corpus, the BERT model achieves a text sentiment classification accuracy of 94.19%, significantly outperforming conventional machine learning paradigms. Predicated on these classifications, a dynamic sentiment index is constructed, revealing that sentiment indicators exhibit a distinct leading effect on closing indices with a horizon of one to two days. Furthermore, by synthesizing sentiment factors with historical transaction characteristics, a temporally enhanced CatBoost prediction model is established. Following rigorous hyperparameter optimization, the model yields a goodness-of-fit ( ) of 0.953 and a mean squared error (MSE) of 0.0097, demonstrating exceptional predictive precision and robustness. The findings underscore that sentiment factors possess substantial explanatory and predictive power regarding short-term stock market volatility, thereby furnishing robust empirical evidence and methodological scaffolding for the development of quantitative investment strategies and financial risk monitoring systems that incorporate natural language processing technologies.
  • 详情 Abnormal Fund Holding Count and Stock Returns
    Existing literature questions whether mutual fund holdings convey information for predicting stock returns in emerging markets. We argue that this lack of evidence stems from a methodological limitation: conventional value-weighted holding measures are dominated by a few large funds, obscuring the collective signal from numerous smaller, but potentially more informed managers. This scale-induced distortion masks the true breadth of institutional attention. To address this, we propose the Abnormal Fund Holding Count (AFHC), defined as the residual from regressing the log number of funds holding a stock on controls for size, value, and liquidity. Using Chinese mutual fund data from 2005 to 2023, we show that AFHC strongly predicts future returns: a long-short portfolio based on AFHC earns an equal-weighted monthly alpha of 1.13\% (t = 4.21), robust to risk adjustments and controlling related return predictors. Moreover, high-AFHC stocks exhibit subsequent improvements in fundamentals and greater price informativeness, consistent with a price discovery channel. Our findings demonstrate that institutional breadth, rather than aggregate capital weight, better reveals informed trading in developing markets.
  • 详情 Overnight Returns, Trading Constraints, and Future Stock Returns: Evidence from the Chinese A-Share Market
    This paper investigates the differential predictive power of overnight and intraday returns in China's A-share market. We find that overnight returns exhibit a significantly positive and robust relation with future stock returns at intermediate horizons, whereas intraday returns display no comparable predictive effect. Mechanism analysis indicates that this predictability is primarily driven by the T+1 trading rule, which restricts timely selling and leads to an underreaction to negative information. Further analyses show that overnight returns embed information about future earnings, suggesting that they capture the delayed incorporation of fundamental news resulting from institutional trading frictions. Our findings differ from patterns documented in developed markets and offer new insights into the price discovery process in emerging equity markets.
  • 详情 Large Language Model and Bond Risk Premia in China
    Using a large language model (LLM), we construct a narrative sentiment index to investigate the predictability of risk premia in the Chinese Treasury bond market. Both in-sample and out-of-sample analyses demonstrate that narrative sentiment significantly and negatively forecasts future bond excess returns, yielding significant economic value for mean-variance investors. By incorporating this measure into an affine term structure model (ATSM), we identify a dual-channel effect: narrative sentiment relates positively to expected future short rates but negatively to excess returns, with the impact intensifying at longer maturities. Risk premia estimated via this sentiment-augmented ATSM exhibit more pronounced countercyclical dynamics. Finally, we establish that narrative sentiment carries forward-looking signals regarding both subjective expectations and future fundamentals, providing a coherent economic foundation for its predictive power in the bond market.
  • 详情 Commodity Risk Mispricing and the Cross-Section of Equity Returns
    We study whether commodity risk is efficiently priced in the cross-section of US equities. We first provide novel evidence on firm-level risk exposure to up to 42 individual commodities. We then construct a mispricing measure as the realized return less the commodity-risk-implied return, and find that it strongly predicts next-month return reversal beyond the traditional short-term reversal. This commodity-risk-mispricing reversal is substantially stronger among small, less analyst- or media-covered stocks, is weakly associated with investor sentiment, and is less prevalent among firms that engage in commodity hedging. In particular, underpricing among these hedgers often remains persistent and even intensifies after the 2004 financialization of commodity markets. This implies that despite the overall decline in mispricing, financialization has likely introduced more costs than benefits for corporate risk management.
  • 详情 Agentic AI Predicts Stock Returns in Real Time
    Can fully agentic artificial intelligence predict equity returns in real time? We build a novel dataset of daily AI-generated attractiveness scores spanning the entire Russell 1000 universe, continuously updated since April 2025. Each trading day, the model freely searches the live internet and produces quantitative scores for every constituent stock before the next market open, eliminating both look-ahead bias and attribution bias. A daily value-weighted portfolio of the 20 highest-ranked stocks earns a Fama-French six-factor alpha of 16.5 basis points per day (41.5% per annum), with an average bid-ask spread of 1.92 basis points. Predictability is sharply asymmetric: the model reliably identifies future outperformers but not future underperformers. The evidence points to stock picking rather than market timing: performance is strongest on down-market days, and the alpha does not come from betting on aggregate market direction. The AI’s reasoning traces help explain this predictability. Alpha is concentrated in traces with richer live-web evidence and stronger analytical structure. In the theme attribution, most active alpha reflects firm selection under an investment lens, not broad theme choice.
  • 详情 Linked Firms’Characteristics and Cross-Stock Predictability in China
    We examine whether the characteristics of economically linked firms predict stock returns in the Chinese A-share market. We construct two peer-based signals: a peeraverage (PA) signal that aggregates the characteristics of fundamentally similar firms, and a peer-deviation (PD) signal that summarizes a firm’s characteristic deviations from industry-peer averages. PA captures shared fundamental information, whereas PD benchmarks a firm’s relative position against economically comparable peers. Portfolio sorts, factor-spanning tests, and Fama–MacBeth regressions reveal economically meaningful and statistically significant return predictability for both signals, with generally larger portfolio returns among non-state-owned enterprises. Both signals retain significant incremental predictive power after controlling for the full set of own-firm characteristics and flexible machine-learning forecasts based solely on these characteristics. Changes in both signals also predict future earnings, while return predictability is generally stronger among firms receiving less investor attention, consistent with limited-attention-induced underreaction. These findings highlight the distinct informational and benchmarking roles of economic networks and their predictive value beyond firms’ own characteristics.
  • 详情 Macroeconomic Expectations and Expected Returns: Evidence from China
    This paper examines whether subjective macroeconomic expectations predict equity risk premia in China. Using professional macro forecasts from the Wind database over 2011- 2023, we construct a composite macroeconomic expectation index via PLS. We find that the index significantly and positively predicts future equity premia both in-sample and out-ofsample, implying a countercyclical equity premium. The predictive power is robust to a wide range of macro-financial controls and delivers economically meaningful gains in portfolio allocation. Further analysis shows that controlling for forecast errors does not attenuate predictability, and the subjective index largely subsumes the information in realized macro variables, suggesting that it captures forward-looking macroeconomic conditions rather than belief bias. Cross-sectional and long-horizon results reinforce this interpretation.
  • 详情 Call option pressure and option return predictability: A U-shaped nonlinearity
    This paper constructs a call pressure index (CP) from China's SSE 50 ETF option market and finds a robust U-shaped nonlinear predictability for directional option returns as measured by log returns. The effect reflects that extreme call pressures—whether unusually low (reversal) or high (momentum)—contain information, while moderate levels are dominated by noise trading. Robustness checks using delta-hedged returns confirm that predictability stems primarily from directional exposure rather than volatility dynamics. The predictability is stronger in high-volatility and down-market states and survives controlling for implied skewness, variance risk premium, and other common predictors. A simple timing strategy based on rolling-window forecasts achieves a Sharpe ratio of 0.97, which further increases to 2.43 after applying a prediction threshold. A parsimonious volume-based indicator captures unique predictive information beyond complex proxies, offering a feasible path for emerging markets lacking proprietary order flow data.
0.223236s