Marketing Research Seminar Series

Observational Learning (OL) is the process by which individuals learn by observing the actions of others. Online platforms increasingly provide statistics that serve as OL information, such as backer counts in crowdfunding, viewership on streaming platforms, and claimed rates in flash sales. While this firm-provided information can facilitate consumer social learning, it is vulnerable to manipulation. This paper identifies a previously undocumented deceptive tactic on Amazon’s Lightning Deals, where sellers artificially inflate the Deal-Claimed Rate (DCR), the real-time percentage of inventory claimed, to mislead consumers. We term this practice 'fake carting.' Analyzing 2.07 million Lightning Deals, we estimate that fake carting occurs in about 1% of all deals, but is heavily concentrated among high-DCR cases. When consumers observe a DCR of 80 percent or higher, there is a 36.5% chance it is manipulated. Holding product, price, and seller constant, we find that fake carting increases the sales effect of Lightning Deals by 23.9%, suggesting consumers are misled into overestimating product value and making suboptimal decisions. Survey evidence shows that consumers place high trust in DCR and remain largely unaware of manipulation. Our findings highlight a significant and underexplored deceptive practice in online markets: the manipulation of OL information.

What types of stories are most persuasive? In this paper, we introduce a new template for categorizing story types based on the specific emotional dynamics of text, or ''emotion sequences''—for example, whether a story begins fearful and ends with sadness, or vice versa. We present this as a new way to capture distinct narrative progressions that is tractable even in short-form media, and then apply this method to analyze the persuasiveness of different story types in online fundraising. Using transformer-based emotion classification tools, we measure the two-part emotion sequences of 14,000 medical fundraising pitches from GoFundMe.org and show that, among other findings, medical fundraising pitches that begin with a sad tone and end on a caring tone are significantly more likely to succeed. We then develop a simple new approach for testing the generalizability of these observational findings by using crowd-sourced, LLM-assisted rewrites to introduce particular emotion sequences to a sample of 40 randomly-selected fundraisers. We show that human-only rewrites generally fail due to skill deficits (and LLM-only rewrites can introduce salient informational changes from originals), but demonstrate that crowd-sourced, LLM-assisted rewriting offers an effective method for testing the out-of-sample application of research results by everyday online users. With this, we establish that pitches rewritten to feature our focal emotion sequences see a significant boost in perceived persuasiveness, even for some sequences associated with lower success in observational data, while placebo rewrites produce null effects. Furthermore, we show that increased identification with the protagonist of the fundraiser is the primary mechanism driving the observed effects.

Can subtle nuances in the way aid is provided negatively impact recipient psychology and behavior? The present research explores the practice of sharing information about and/or a message from the giver to the aid recipient—what we term giver spotlighting—a marketing practice employed by sponsorship charities and community-based aid programs. Six preregistered experiments (N = 3,888), a Kenya-based field study and a series of five online experiments, explore the effect of giver spotlighting on recipients' willingness to recommend the aid organization to others in similar need states and return for more aid if it is needed, hence, examining potential knowledge spread of the aid opportunity and continued aid take-up. Our results suggest that giver spotlighting threatens recipients' self-efficacy and, subsequently, hinders recipients' willingness to recommend the aid program and to return if more help is needed. The present research provides novel insights into how aid organizations can create more effective campaigns that bring in more recipients while also improving existing recipients' experiences when utilizing their aid program.

Visual designs are often used in marketing (e.g., packaging, ads, media covers) to achieve a variety of business outcomes, like improved sales, click-through rates, and brand attitudes. Since designs are complex, unstructured data, it is difficult to determine what features drive their success in a way that is interpretable and managerially actionable. To address this challenge, I develop a novel methodological framework to automatically discover what interpretable features make visual designs in a given domain successful. I first leverage a deep generative text-to-image AI model (by fine-tuning Stable Diffusion 3.5 in my application) that adopts the role of designer and enables visual designs to be described by low-dimensional design representations. Then, I apply a novel adaptation of cutting-edge ''mechanistic interpretability'' methods—specifically ''sparse autoencoders'' typically applied to large language models—to scalably discover a taxonomy of interpretable and managerially relevant features predictive of success from these design representations. Finally, I generate image redesigns by manipulating features of interest to help managers scalably pilot data-driven design changes. I apply this framework to discover how book cover redesigns predict sales on Amazon.com using a unique dataset I collected of over 160,000 books. I discover a diverse set of interpretable features related to illustration, typography, composition, and layout. I then create realistic cover redesigns predicted to improve sales by manipulating those features (e.g., redesigns with lower contrast and less separation of text and graphical elements). In a holdout analysis with a rich set of control variables, including just 30 of these discovered features (out of 9,728) improves variation explained in sales by nearly as much as prices and by more than reviews. Back-of-the-envelope calculations suggest that a large publisher could leverage this subset of features to increase annual revenue by over $9.1 million, reflecting a change in sales equivalent to introducing an 8.5% price discount.

We study teachers' usage of a digital differentiation tool designed for reading comprehension assignments on an educational technology platform and examine the role of teacher usage in shaping the effectiveness of this tool. Using a structural model that incorporates a hidden Markov model and a two-stage framework for teachers' differentiation decisions, we investigate teachers' usage and implementation preference and evaluate the tool’s effectiveness in enhancing student performance and addressing achievement gaps. First, we find that overall usage of the tool is low, with even lower usage in high-poverty schools. Among those who do use the tool, implementation preferences differ by socioeconomic segment: teachers in high-poverty schools are more likely to prioritize higher-achieving students. Second, through counterfactual simulations, we find that while observed actual usage provides only modest benefits, full usage leads to significant improvements in student performance, particularly in low-poverty schools. To address the gap between potential and actual use, we analyze platform-led interventions. Reducing the cost of implementation increases usage but disproportionately benefits low-poverty schools. A combined strategy that includes both cost reduction and targeted training for teachers in high-poverty schools improves teacher usage and student outcomes across socioeconomic segments. These findings highlight the importance of addressing usage barriers in realizing the full benefit of educational technologies.

Peer-to-peer payment platforms such as Venmo have profoundly transformed social and financial interactions, generating rich behavioral, relational, and network data. Yet, understanding the dynamics of user engagement and growth dynamics in non-contractual settings remain challenging. This study proposes a unified framework, the Multi-Stream Temporal Graph Neural Network (MuST-GNN), that integrates transactional patterns, linguistic features, and network structure. Designed as a joint-task model, it predicts two behavioral outcomes critical to platform growth: engagement among existing users and the acquisition of new users through first-time interactions. Using comprehensive data from Venmo's early growth period and evaluated in a live-update setting, the findings are threefold. First, MuST-GNN substantially outperforms both CRM-based and graph-only models, with predictive improvements of over 30% for engagement and nearly 20% for acquisition relative to a baseline that excludes multimodal signals. Second, linguistic signals provide the strongest predictive lift, highlighting the relational and contextual value embedded in transaction notes and emojis. Third, attention analyses show that the model dynamically shifts its reliance on different modalities over time. Network position is more predictive when little behavioral history exists, transaction patterns become more important as user activity grows, and language signals dominate as social ties deepen. This research provides a robust framework for understanding how social connections, financial behaviors, and communication jointly drive consumer engagement and growth on networked platforms.

Consumers are often drawn to offers that promise unlimited access to a product or service (e.g., unlimited monthly mobile plans). Because actual consumption opportunities are typically finite, most explicitly unlimited offers (e.g., ''unlimited minutes per month'') could be reframed as superficially limited (e.g., '' 44,640 minutes per month''). Although explicitly unlimited offers are seen as more subjectively valuable (i.e., attractive), superficially limited offers win out on monetary valuation (i.e., willingness to pay, estimated price). Two processes explain why superficially limited frames—despite imposing superficial constraints—elevate valuation. First, their high discrete usage limits serve as anchors that increase anticipated usage. Second, these limits permit comparisons with other (necessarily smaller) finite offers that are simpler to price. Consumers spontaneously recruit and scale up from these reference prices when assessing a superficially limited offer's monetary value. The extent to which a consumer's interest in or preference for an offer is predicted by subjective versus monetary valuation—and thus which offer frame dominates—depends on how preferences are elicited and what information consumers have access to (e.g., prices). This work moves research on unlimited offers in a qualitatively new direction and illustrates the theoretical and practical importance of distinguishing between subjective and monetary valuation.

Consumers increasingly encounter products and services positioned to support mental wellness, yet little is known about how they perceive these offerings. This research demonstrates that consumers perceive mental wellness offerings to be more luxurious relative to physical wellness offerings and documents a novel lay belief that underlies this perception. Consumers believe the pursuit of mental wellness is a luxury—desirable but non-essential, and a symbol of exclusivity for those with surplus resources. This lay belief drives greater luxury perceptions of mental wellness offerings even when the same product is advertised to support mental rather than physical wellness. These enhanced luxury perceptions of mental wellness offerings, in turn, increase purchase intentions, particularly when consumers are motivated by a desire to consume luxury. Further supporting the role of the lay belief, luxury perceptions of mental wellness offerings arise in health maintenance contexts but not in treatment contexts, where such products are seen as more of a necessity, rendering the lay belief less applicable. The practical implications of these insights for brand and product positioning, product development, and advertising are discussed.

When analyzing a sequence of customer interactions, it is important for firms to understand how these interactions align with key objectives, such as generating qualified customer leads, driving conversion events, or reducing churn. We introduce a transformer-based framework that models customer interactions in a sequence similar to how a sentence is modeled as a sequence of words by Large Language Models. We propose a heterogeneous mixture multi-head self-attention mechanism that captures individual heterogeneity in touchpoint effects. The model identifies self-attention patterns that reflect both population-level trends and the unique relationships between touch points within each customer journey. By assigning varying weights to each attention head, the model accounts for the distinctive aspects of the journey of each user. This results in more accurate predictions, enabling precise targeting and outperforming existing approaches such as hidden Markov models, point process models, and LSTMs. Our empirical application in a multichannel marketing context demonstrates how managers can leverage the model's features to identify high-potential customers for targeting. Extensive simulations further establish the model's superiority over competing approaches. Beyond multichannel marketing, our transformer-based model also has broad applicability in customer journeys across other domains.

Serialized content—such as episodic fiction, TV series, or educational courses—presents consumers with a dynamic choice: pay for immediate access, wait for free access, or quit. These decisions are shaped not only by platform policies but also by the content itself. Understanding how these factors jointly influence consumption is critical for platforms aiming to optimize engagement and monetization. Content, however, is high-dimensional (capturing multiple layers of meaning and narrative structure) posing challenges for traditional estimation methods. We address this challenge by extending adversarial inverse reinforcement learning (AIRL)—a GAN-based estimator that recovers reward and policy functions from observed behavior. Methodologically, we (i) prove identifiability of action-dependent utilities, (ii) incorporate unobserved consumer heterogeneity, and (iii) develop a content representation method that map unstructured text into features predictive of engagement and payment. We apply the model to 15 months of reading data from a serialized fiction platform (24,000 users, 6,000 chapters, 151 books). Estimates reveal two dominant segments—''Pay & Read'' and ''Wait & Read''—that together account for 87% of consumption and 99% of purchases. Validation against field experiments shows that the estimated rewards are stable and disentangled from environment dynamics. Counterfactuals yield three key insights. First, providing content for free can counterintuitively increase purchases within the consumer, by allowing them to move past likely churn points and creating additional purchase opportunities. Second, customized policies based on heterogeneous patience can increase consumption and purchases by 4% and 23%, respectively. Third, leveraging unstructured content to align pricing with narrative peaks can significantly boost monetization. More broadly, we introduce adversarial estimation as a scalable tool for dynamic models with high-dimensional states.

Retail media, a fast-growing channel for digital advertising, surpassed $55 billion of ad spend in 2024. A common retail media format involves position auctions, in which advertisers bid for higher placements on a retailer's product listing page. Advertiser bids are combined with a retailer-set quality score to determine the allocation of sponsored slots and the resulting payments. Quality scores boost certain advertisers' positions and reduce their per-click price. Unlike search engine advertising, retail media position auctions can monetize sales commissions as well as clicks. This paper develops a quality score approach to effectively balance these monetization options. To connect quality scores to retail revenues, the paper develops a structural model linking advertiser bids and revenues to the retailer's quality score choices coupled with a machine learning model of consumer behavior. These models are estimated using auction-advertiser level data from a quality score experiment conducted at a mid-size US based retail marketplace. Policy simulations show that a quality score approach that balances clicks and commissions improves retailer profits by 7% and advertiser surplus by 42% over click-based approaches typically used by retailers, leading to a win-win outcome for both.

This article provides evidence on the impact of workforce gender diversity on individual-level performance in a microfinance firm in Mexico. Despite increased confidence from recent research in diversity's effects on group-level performance, direct evidence is absent on whose performance within groups increases (more) due to demographic diversity. Leveraging the firm's random transfer policy, we initially do not find evidence of the impact of gender diversity on individual officers' loan collection performance however, further investigation reveals substantial heterogeneity especially by loan officer gender. Male loan officers perform best in gender-balanced branches while underperforming in predominantly male or female branches. Female loan officers, by contrast, show stable performance regardless of the workforce composition. We further explore potential mechanisms behind this impact whether it comes from learning skills for better performance or from getting temporary access to more diverse information in a gender-diverse branch.

Doctoral Student Research Presentations

Welcome and Keynote Address

Introducing a new currency in an existing market offers a potentially influential, alternative currency option—a prediction that prompts the current research into how consumers evaluate cryptocurrencies and the effects on their spending. Nine studies consistently demonstrate that paying with cryptocurrencies reduces purchase intentions, mediated by the pain of payment. However, if a cryptocurrency is positioned as a payment mechanism, consumers' purchase intentions remain similar to those they express for fiat currencies. This mental accounting explanation is confirmed with field data. The authors also demonstrate that the negative impact can be mitigated if the cryptocurrency is introduced as a virtual currency. Finally, the negative impact of cryptocurrencies is mitigated for higher priced products. These results offer important theoretical insights into how payment mechanisms affect purchases, as well as managerial insights about how cryptocurrency providers and retailers can increase uses of cryptocurrency as a payment mechanism.

Self-disclosures, or the voluntary sharing of information about one's vulnerabilities, are common among persuasion agents such as online influencers, entrepreneurs, and marketers. While prior research highlights the 'disclosure-liking effect,' where self-disclosures increase trust and positive evaluations, we investigate the conditions under which self-disclosures may backfire. Drawing on persuasion knowledge theory, we show that self-disclosures by persuasion agents can elicit inferences of manipulative intent (IMI), leading to reduced liking, crowdfunding interest, and purchase intentions. Further, drawing on attribution theory, we demonstrate that perceived controllability moderates the effect of self-disclosures on consumer responses. When the disclosed issue is attributed to causes controllable by the persuasion agent (e.g., overspending), IMI is heightened, reducing liking and consumer support conversely, when the issue is attributed to uncontrollable causes (e.g., genetic diseases), self-disclosures elicit sympathy, enhancing liking. These findings introduce IMI as a novel consequence to self-disclosures in the marketplace and controllability as a key moderator. Substantively, this research speaks to the double-edged nature of self-disclosures, providing insights for persuasion agents navigating the fine line between authentic engagement and perceived manipulation.

Online content-sharing platforms such as TikTok and Facebook have become integral to daily life, leveraging complex algorithms to recommend user-generated content (UGC) to other users. While prior research and industry efforts have primarily focused on designing recommender systems to enhance users' content consumption, the impact of recommender systems on content production remains understudied. To address this gap, we conducted a randomized field experiment on one of the world's largest video-sharing platforms. We manipulated the algorithm's recommendation of creators based on their popularity, excluding a subset of highly popular creators' content from being recommended to the treatment group. Our experimental results indicate that recommending content from less popular creators led to a significant 1.34% decrease in video-watching time but a significant 2.71% increase in the number of videos uploaded by treated users. This highlights a critical trade-off in designing recommender systems: popular creator recommendations boost consumption but reduce production. To optimize recommendations, we developed a structural model wherein users' choices between content consumption and production are inversely affected by recommended creators' popularity. Counterfactual analyses based on our structural estimation reveal that the optimal strategy often involves recommending less popular content to enhance production, challenging current industry practices. Thus, a balanced approach in designing recommender systems is essential to simultaneously foster content consumption and production.

Digital advertising, which uses consumer data to target ads to users, now accounts for most of global ad expenditures. Privacy concerns have prompted regulations that restrict the use of personal data. To inform these policy debates, we develop an equilibrium model of advertising and market structure to analyze the impact of privacy regulation on market outcomes. We test the model's predictions using the launch of Apple's App Tracking Transparency feature, which created a natural experiment that limited the use of consumer data. Leveraging data from all U.S. advertisers on Meta combined with offline administrative data, we find that reductions in digital ad effectiveness led to decreases in investments in advertising, increases in market concentration, and increases in product prices. These effects are economically meaningful in magnitude and suggest potential harms to both firms and consumers from privacy regulation.

Firms often need to develop a timing policy for interventions in response to a customer action. Examples include how long to wait before sending an online review request after a purchase, and time until sending a promotional offer to shopping cart abandoners. Causal inference in such settings, especially when the timeline for intervention can be over an extended period (e.g., a few weeks), is not straightforward due to the ''triple hurdle'' problem. That is, customers (1) need to enter the sample by taking an action, (2) comply with the intervention timing intended by the firm, and (3) choose their response to the intervention. We present a quasi-experiment design that can recover intervention treatment effects by timing when randomization into treatment and control groups is possible but random assignment to intervention timing is not. Specifically, we use (1) propensity score matching using a rich pre-treatment customer history to match the distribution of customer types across customer cohorts, (2) random assignment to treatment and control groups generating an exclusion restriction for the customer outcome equation, and (3) estimation of a conditional average treatment effects as a function of intervention timing. We discuss how the proposed design can allow a firm to test the effectiveness of interventions by timing while minimizing campaign duration and exposure to the intervention amongst the customer base. We demonstrate our approach in the context of shopping cart interventions that target customers leaving an item unpurchased in their online cart and find an inverted U-shaped lift pattern for intervention timing using a discount coupon.

People who persuade can use language that differs in average and variation of certainty. While higher average certainty has been shown to enhance persuasion, excessive certainty may harm it, and the impact of certainty variation has been overlooked. This research uses multiple methods to investigate. We analyze the transcripts of 7,811 sales calls, finding that higher average certainty generally boosts purchase likelihood, though too much certainty can backfire. Notably, at high levels of average certainty, greater variation in certainty reduces its positive effect. Pre-registered scenario-based experiments confirm key findings, showing that perceptions of persuader confidence and credibility mediate these effects, with uncertainty about controllable aspects being particularly harmful to evaluations and purchase intention. This study offers key insights for persuasion and source certainty.