Business Analytics

Our faces are said to be windows into the soul. But can they also reflect who we are as consumers? Can facial images predict brand preferences? To answer these questions, we analyze a unique dataset of over 100,000 single-face Twitter profile pictures linked with brand followership data for 444 brands across categories and brand personality metrics. Using advanced machine learning for automated face analysis, we demonstrate that consumers’ social media profile faces can reveal their preferences between rival brands (study 1).

As generative AI systems rapidly improve, a key question emerges: how do users adapt to these changes, and when does such adaptation matter for realizing performance gains? This paper studies prompt adaptation—how users adjust their inputs in response to evolving model behavior—using a common experimental design applied to two preregistered tasks with 3,750 total participants who submitted nearly 37,000 prompts. We show that the importance of prompt adaptation depends critically on task structure.

Screening human capital based on signals such as job applications or entrepreneurial pitches is crucial for organizations. Signals are often informative insofar as they require differential knowledge and effort to produce. Generative AI (GAI) complicates screening by lowering the cost of producing impressive signals. We model the informational effects of GAI, showing that applicants' access to GAI can increase—but also decrease—an evaluator's screening mistakes. This result depends on how GAI affects experts' signals compared to non-experts'.

Major life transitions, such as pregnancy and childbirth, reshape lifestyles and purchasing priorities, yet causal evidence on how consumers reallocate spending across product categories remains limited. We quantify the effects of first-time parenthood by linking a large-scale transactional panel to verified birth records. To identify causal effects, we implement a difference-in-differences design augmented with causal forests, enabling flexible comparisons between households entering parenthood and carefully matched controls. We uncover a pronounced and dynamic behavioral trajectory.

Firms increasingly rely on A/B testing to evaluate marketing strategies, yet most experiments are analyzed in isolation, limiting insight into why effectiveness varies and how repeated exposure shapes outcomes. We develop a hierarchical Bayesian framework that jointly analyzes randomized marketing interventions to decompose treatment effect heterogeneity into three components: customer responsiveness, campaign design, and contextual timing.

We employ machine learning methods to identify skill among active bond mutual fund managers. Using a comprehensive dataset of 3,021 unique U.S. bond funds from May 1995 to November 2024, we demonstrate that fund-level and family-level characteristics, particularly past performance metrics, reliably predict future bond fund performance. A prediction-weighted portfolio strategy that goes long the best-10% of funds and short the worst-10% of funds generates monthly abnormal returns of 30 basis points with an information ratio of 24.6%. The outperformance persists for up to 36 months.

We study the dynamic pooling of multiple orders into a single trip, a strategy widely adopted by online delivery platforms. When an order has to be dispatched, the platform must determine which (if any) of the available orders to pool it with, weighing the immediate efficiency gains against the uncertain, differential benefits of holding each order for future pooling opportunities. In this paper, we demonstrate the effectiveness of using the delivery distance as a proxy for opportunity cost via a potential-based greedy algorithm (PB).

In the Newsvendor problem, the goal is to guess the number that will be drawn from some distribution, with asymmetric consequences for guessing too high vs. too low. In the data-driven version, the distribution is unknown, and one must work with samples from the distribution. Data-driven Newsvendor has been studied under many variants: additive vs. multiplicative regret, high probability vs. expectation bounds, and different distribution classes. This paper studies all combinations of these variants, filling in many gaps in the literature and simplifying many proofs.

Salespeople frequently face the dynamic screening decision of whether to persist in a conversation or abandon it to pursue the next lead. Yet, little is known about how these decisions are made, whether they are efficient, or how to improve them. We study these decisions in the context of high-volume outbound sales where leads are ample, but time is scarce and failure is common.