Research
Seminars
Filter results | Clear Filters
8:00 AM - 5:00 PM
TBD
Marketing Camp
-
Marketing Camp
Speaker: TBD
Time: 8:00 AM - 5:00 PM
Location:
12:30 PM - 2:00 PM
Lan Luo: Columbia University
How Visual Designs Drive Success: Interpretable Generative AI for Data-Driven Design
-
How Visual Designs Drive Success: Interpretable Generative AI for Data-Driven Design
Speaker: Lan Luo: Columbia University
Time: 12:30 PM - 2:00 PM
Location:
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.
12:30 PM - 2:00 PM
Amanda Geiser: UC Berkeley
The Limits of “Unlimited” Offers: How Quantifying Constraints Can Increase Valuation
-
The Limits of “Unlimited” Offers: How Quantifying Constraints Can Increase Valuation
Speaker: Amanda Geiser: UC Berkeley
Time: 12:30 PM - 2:00 PM
Location:
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.
12:30 PM - 2:00 PM
Anya Shchetkina: University of Pennsylvania
Blind Targeting: Personalization under Third-Party Privacy Constraints
-
Blind Targeting: Personalization under Third-Party Privacy Constraints
Speaker: Anya Shchetkina: University of Pennsylvania
Time: 12:30 PM - 2:00 PM
Location:
Major advertising platforms have recently increased privacy protections by limiting advertisers’ access to individual-level data. Instead of providing access to the granular raw data, the platforms only allow a limited number of aggregate queries to a dataset, which is further protected by adding differentially private noise. This paper studies whether and how advertisers can design effective targeting policies within these restrictive privacy preserving data environments. To achieve this, I develop a method based on Bayesian optimization that includes two innovations over the classic setup: (i) integral updating of posterior which allows to select best regions to query rather than points and (ii) targeting-aware acquisition function that dynamically selects regions most informative for the targeting task. I identify the conditions of the dataset and privacy environment that necessitate the use of such a “smart” querying strategy. I also show when a simple strategy, such as uniform binning, is sufficient. Finally, I apply the strategy to the Criteo AI Labs dataset for uplift modeling. I show that a simple benchmark strategy fails under differential privacy requirement in some settings. However, the strategic querying method delivers a robust performance that achieves the same level as a non-privacy-protected state-of-the-art machine learning method.
12:30 PM - 2:00 PM
Magie Cheng
Balancing Engagement and Polarization: Multi-Objective Alignment of News Content Using LLMs
-
Balancing Engagement and Polarization: Multi-Objective Alignment of News Content Using LLMs
Speaker: Magie Cheng
Time: 12:30 PM - 2:00 PM
Location:
We study how media firms can use LLMs to generate news content that aligns with multiple objectives – making content more engaging while maintaining a preferred level of polarization/slant consistent with the firm’s editorial policy. Using news articles from The New York Times, we first show that more engaging human-written content tends to be more polarizing. Further, naively employing LLMs (with prompts or standard Direct Preference Optimization approaches) to generate more engaging content can also increase polarization. This has an important managerial and policy implication: using LLMs without building in controls for limiting slant can exacerbate news media polarization. We present a constructive solution to this problem based on the Multi-Objective Direct Preference Optimization (MODPO) algorithm, a novel approach that integrates Direct Preference Optimization with multi-objective optimization techniques. We build on open-source LLMs and develop a new language model that simultaneously makes content more engaging while maintaining a preferred editorial stance. Our model achieves this by modifying content characteristics strongly associated with polarization but that have a relatively smaller impact on engagement. Our approach and findings apply to other settings where firms seek to use LLMs for content creation to achieve multiple objectives, e.g., advertising and social media.
12:30 PM - 2:00 PM
Ethan Milne: Western University
How Political Ideology Shapes Prosocial Consumer Behavior Research
-
How Political Ideology Shapes Prosocial Consumer Behavior Research
Speaker: Ethan Milne: Western University
Time: 12:30 PM - 2:00 PM
Location:
The current investigation suggests that a lack of political diversity exists in the stimuli used in prosocial consumer behavior research, which poses challenges for the reliability and generalizability of such work. We review prosocial consumer behavior research from the leading marketing journals across twenty years and show that the study stimuli therein exhibit a consistent liberal skew. In a survey of contemporary prosocial consumer behavior researchers, we identify that the political beliefs of researchers and bias against conservative cause areas likely explain the observed political skew of stimuli in prosocial consumer research. Finally, two primary and three supplementary experiments demonstrate that unacknowledged political leaning of prosocial stimuli, and the unmeasured political beliefs of participants, can distort estimates of prior findings and theory if not accounted for in a thoughtful manner. This work contributes to the literature on prosocial consumer behavior by identifying a bias in stimuli selection that has resulted in an incomplete and distorted understanding of important theoretical frameworks and thus has likely hampered our knowledge of the full nature of prosocial consumer behavior.
12:30 PM - 2:00 PM
Ximena Garcia-Rada: Texas A&M University
The Time-Unboundedness of Caregiving: Why Caregiving Responsibilities Decrease the Likelihood of Choosing Leisure
-
The Time-Unboundedness of Caregiving: Why Caregiving Responsibilities Decrease the Likelihood of Choosing Leisure
Speaker: Ximena Garcia-Rada: Texas A&M University
Time: 12:30 PM - 2:00 PM
Location:
Many consumers have major time-consuming and oft-stressful responsibilities—such as caregiving, work, and school. The present research examines how caregiving responsibilities affect consumers’ choices, focusing on whether, why, and when caregiving responsibilities, compared to other major responsibilities (e.g., work and school), may uniquely discourage the choice of leisure consumption. Across a series of preregistered studies, primarily focused on working parents, reminding consumers of their caregiving responsibilities (vs. other major responsibilities) decreased their likelihood of choosing leisure. One key reason is that compared to other major responsibilities, consumers perceive caregiving responsibilities as more “time-unbounded” (i.e., as responsibilities that are more continuous over time, without well-defined limits, and unable to be checked off as completed for a given period of time), thereby decreasing the likelihood of choosing leisure. Therefore, process-consistent interventions that blur the boundaries between caregiving responsibilities and leisure consumption—such as leisure-bundling (i.e., solo leisure consumption at the same time as performing caregiving responsibilities) and co-leisure (i.e., engaging in leisure consumption together with the care-recipient)—can increase the likelihood of choosing leisure. Altogether, this research contributes to understanding and addressing the consumer well-being challenges that are uniquely associated with caregiving responsibilities.