Category Archives: Working Papers

Competition Against Itself: Search Dilution and Inactivation

Koh, Yumi, Gea M. Lee, Gene Moo Lee (2026) “Competition Against Itself: Search Dilution and Inactivation”. Working Paper. [Latest version: August 2026] [SSRN]

When does competition discipline prices? The answer depends on how consumer search responds to competition. We develop an incomplete-information model where firms price under private cost heterogeneity and consumers choose between immediate purchase and sequential search. Search regimes–inactive or active–emerge endogenously from cost heterogeneity, the search cost, and market thickness. Under inactive search, competition can trigger a search-dilution effect that pushes the expected price upward. Under active search, competition instead erodes price dispersion as the market thickens, causing the regime to contract or collapse. Either way, competition can thus undermine the very search channel of price discipline.

IT Risk and Stock Price Crash Risk

Song, Victor, Hasan Cavusoglu, Jaecheol Park, Mary L. Z. Ma, Gene Moo Lee (2026) “IT Risk and Stock Price Crash Risk,” Under review.

This study examines whether and how firm-level information technology (IT) risk contributes to stock price crash risk. We construct a novel measure of ex-ante IT risk from risk factor disclosures in Item 1A of firms’ 10-K filings using advanced machine learning approaches. We find that higher IT risk is associated with greater stock price crash risk. Mechanism analyses indicate that this effect operates primarily through increased downside operating risk, rather than through heightened exposure to data breach events. We further document heterogeneity in the relationship between IT risk and stock price crash risk: (1) cybersecurity risk has a stronger effect than noncybersecurity IT risk; (2) the effect is stronger for newly disclosed IT risk factors; and (3) higher readability amplifies the crash risk effect. Together, these findings highlight IT risk as a previously underexplored determinant of stock price crash risk and offer new insights into the capital market consequences of firms’ IT-related disclosures.

Predicting Litigation Risk via Machine Learning

Lee, Gene Moo*, James Naughton*, Xin Zheng*, Dexin Zhou* (2020) “Predicting Litigation Risk via Machine Learning,” Working Paper. [SSRN] (* equal contribution)

This study examines whether and how machine learning techniques can improve the prediction of litigation risk relative to the traditional logistic regression model. Existing litigation literature has no consensus on a predictive model. Additionally, the evaluation of litigation model performance is ad hoc. We use five popular machine learning techniques to predict litigation risk and benchmark their performance against the logistic regression model in Kim and Skinner (2012). Our results show that machine learning techniques can significantly improve the predictability of litigation risk. We identify two best-performing methods (random forest and convolutional neural networks) and rank the importance of predictors. Additionally, we show that models using economically-motivated ratio variables perform better than models using raw variables. Overall, our results suggest that the joint consideration of economically-meaningful predictors and machine learning techniques maximize the improvement of predictive litigation models.