Paper: arXiv 2505.16287
Authors: Abdullah Karasan, Ozge Sezgin Alp, Gerhard-Wilhelm Weber
Abstract
In this study, we propose a novel machine-learning-based measure for stock price crash risk, utilizing the minimum covariance determinant methodology. Employing this newly introduced dependent variable, we predict stock price crash risk through cross-sectional regression analysis. The findings confirm that the proposed method effectively captures stock price crash risk, with the model demonstrating strong performance in terms of both statistical significance and economic relevance. Furthermore, leveraging a newly developed firm-specific investor sentiment index, the analysis identifies a positive correlation between stock price crash risk and firm-specific investor sentiment. Specifically, higher levels of sentiment are associated with an increased likelihood of stock price crash risk. This relationship remains robust across different firm sizes and when using the detoned version of the firm-specific investor sentiment index, further validating the reliability of the proposed approach.
Complexity vs Empirical Score
- Math Complexity: 5.0/10
- Empirical Rigor: 6.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper employs advanced machine learning (Minimum Covariance Determinant) for anomaly detection and uses panel regression with statistical significance testing, showing moderate mathematical sophistication. It is data-heavy, backtest-ready with a focus on robustness checks, firm-specific sentiment index, and cross-sectional analysis, indicating high empirical implementation.
Research Flowchart
flowchart TD A["Research Goal: Predict Stock Price Crash Risk"] --> B["Data Input: Stock Returns & Financial Data"] B --> C["Compute New Measure: Minimum Covariance Determinant"] C --> D["Methodology: Cross-Sectional Regression Analysis"] D --> E["Compute Firm-Specific Investor Sentiment Index"] D --> F["Identify Correlation: Sentiment vs. Crash Risk"] E --> F F --> G["Key Finding: Positive Correlation Confirmed"] F --> H["Key Finding: Robust Across Firm Sizes & Detoned Index"] G --> I["Outcome: Validated ML Approach & Economic Relevance"] H --> I
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes a novel machine‑learning‑based measure for stock price crash risk using the Minimum Covariance Determinant (MCD) methodology.
Source sentence
In this study, we propose a novel machine-learning-based measure for stock price crash risk, utilizing the minimum covariance determinant methodology.
Assumes 3
- MCD detection assumes the data distribution is elliptically symmetric and unimodal. model
Source sentence
MCD is a method proposed to detect anomalies in a distribution with elliptically symmetric and unimodal dataset.
- Firms must have at least 10% non‑zero returns during the sample period. data
Source sentence
Companies with less than 10% non-zero returns during the sample period were excluded, as their trading activity was deemed insufficient to yield meaningful insights.
- Firms must have at least five weekly return observations. data
Source sentence
Firms with fewer than five weekly return observations were also removed to mitigate the risk of distorted results from limited data points.
Data
- CRSP market-prices public
Source sentence
The data for this study was collected from the Center for Research in Security Prices (CRSP) and Compustat. The sample includes publicly traded North American companies listed on the New York Stock Exchange (NYSE) and NASDAQ. Weekly stock returns and returns on the value-weighted market index were sourced from CRSP...
- Compustat fundamentals commercial
Source sentence
balance sheet data and other stock-related information were retrieved from the merged Compustat/CRSP database.
Costs
Not applicable
Finds 5
- The MCD‑based crash risk measure captures stock price crash risk with strong statistical significance and economic relevance. statistical
Source sentence
The findings confirm that the proposed method effectively captures stock price crash risk, with the model demonstrating strong performance in terms of both statistical significance and economic relevance.
- Higher firm‑specific investor sentiment is positively associated with increased stock price crash risk, robust across firm sizes and after detoning the sentiment index. statistical
Source sentence
Specifically, higher levels of sentiment are associated with an increased likelihood of stock price crash risk. This relationship remains robust across different firm sizes and when using the detoned version of the firm-specific investor sentiment index...
- Among machine‑learning classifiers, the Decision Tree achieves the lowest RMSE (0.62), outperforming Random Forest (0.64) and XGBoost (0.68). predictive-accuracy
Source sentence
The Decision Tree model achieves the lowest RMSE (0.62), followed by Random Forest (0.64) and XGBoost (0.68).
- Feature importance analysis shows turnover ratio as the most impactful predictor, followed by firm‑specific sentiment and negative skewness; ROA reduces crash risk and firm size has minimal influence. performance
Source sentence
Turnover (dturn) emerges as a significant factor, with higher values substantially increasing crash risk. Similarly, firm‑specific sentiment positively correlates with crash risk
- The MCD‑based crash risk measure aligns with established measures such as negative skewness, down‑to‑up volatility, and traditional crash risk indicators. statistical
Source sentence
The performance of the MCD‑based crash risk measure is found to align with well-established measures such as negative skewness, down-to-up volatility, and traditional crash risk indicators.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 31 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.
Cited References (46)
- Foreign investors and stock price crash risk: Evidence from China (2020) — link
- Does investor sentiment affect stock price crash risk? (2020) — link
- Machine Learning for Asset Managers (Chapter 1) (2020)
- How Do Corporate Social Responsibility and Corporate Governance Affect Stock Price Crash Risk? (2020) — link
- Firm-specific investor sentiment and stock price crash risk (2020) — link
- Firm-specific investor sentiment and daily stock returns (2019) — link
- Can investor sentiment predict the size premium? (2019) — link
- Foreign Investors and Stock Price Crash Risk: Evidence from Vietnam (2018) — link
and 38 more
- Is Real Earnings Smoothing Harmful? Evidence from Firm‐Specific Stock Price Crash Risk (2018) — link
- Minimum covariance determinant and extensions (2017) — link
- CEO age and stock price crash risk (2017) — link
- Investor Sentiment, Financial Report Quality and Stock Price Crash Risk: Role of Short-Sales Constraints (2017) — link
- Earnings Smoothing: Does It Exacerbate or Constrain Stock Price Crash Risk? (2017) — link
- Internal Control and Stock Price Crash Risk: Evidence from China (2017) — link
- Corporate Philanthropy and Stock Price Crash Risk: Evidence from China (2016) — link
- CEO Overconfidence and Stock Price Crash Risk (2016) — link
- Political connections and stock price crash risk: Evidence from China (2016) — link
- Directors’ and officers’ liability insurance and stock price crash risk (2016) — link
- Stock Liquidity and Stock Price Crash Risk (2016) — link
- Detecting stock market manipulation using supervised learning algorithms (2014) — link
- Financial Reporting Opacity and Expected Crash Risk: Evidence from Implied Volatility Smirks (2014) — link
- Corporate Social Responsibility and Stock Price Crash Risk (2014) — link
- Institutional Investor Stability and Crash Risk: Monitoring versus Short-Termism? (2013) — link
- Stock Price Synchronicity, Crash Risk, and Institutional Investors (2013) — link
- Changes in Cross-Correlations as an Indicator for Systemic Risk (2012) — link
- Distribution of Variables by Method of Outlier Detection (2012) — link
- Corporate Tax Avoidance and Stock Price Crash Risk: Firm-Level Analysis (2011) — link
- Investor Sentiment and Market Anomalies (2010) — link
- Econometric Measures of Systemic Risk in the Finance and Insurance Sectors (2010) — link
- Opaque financial reports, R2, and crash risk (2009) — link
- Corporate Governance and Conditional Skewness in the World’s Stock Markets (2006) — link
- The Distribution of Robust Distances (2005) — link
- Forecasting Crashes: Trading Volume, Past Returns and Conditional Skewness in Stock Prices (1999) — link
- Some Tests of Specification for Panel Data: Monte Carlo Evidence and an Application to Employment Equations (1991) — link
- Noise Trader Risk in Financial Markets (1990) — link
- Expected stock returns and volatility (1987) — link
- The stochastic behavior of common stock variances: value (1982) — link
- Bubbles, Rational Expectations and Financial Markets (1982) — link
- Early warning on stock market bubbles via methods of optimization, clustering and inverse problems (2018) — link
- Investor sentiment in the stock market (2013)
- Around the World : New Theory and New Tests (2004)
- Working Paper Series ASSET MANAGEMENT Research Group INVESTOR SENTIMENT AND THE CROSS-SECTION OF STOCK RETURNS (2003)
- Principal Component Analysis for Special Types of Data (1986) — link
- Studiesofstockmarketvolatilitychanges (1976)
- Systematic analysis of group identification in stock markets
- Firms with fewer than five weekly return observations were also removed to mitigate the risk of distorted results from limited data points
0 of 46 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.