A5052730753- Consumer Market Behavior and Pricing
- Economic and Environmental Valuation
- Customer churn and segmentation
- Digital Platforms and Economics
- Consumer Behavior in Brand Consumption and Identification
- Digital Marketing and Social Media
- Statistical Methods and Bayesian Inference
- Advanced Causal Inference Techniques
- Auction Theory and Applications
- Decision-Making and Behavioral Economics
- Statistical Methods in Clinical Trials
- Data Analysis with R
- Energy, Environment, and Transportation Policies
- Consumer Retail Behavior Studies
- Statistical Methods and Inference
- Advanced Statistical Methods and Models
- Customer Service Quality and Loyalty
- Marketing and Advertising Strategies
- Electric Vehicles and Infrastructure
- Bayesian Methods and Mixture Models
- Innovation Diffusion and Forecasting
- Reproductive Physiology in Livestock
- Opinion Dynamics and Social Influence
- Technology Adoption and User Behaviour
- Nonmelanoma Skin Cancer Studies
Drexel University
2016-2025
University of Pennsylvania
2011-2019
University of Michigan
2006-2010
Ross School
2006
Advances in data collection have made it increasingly easy to collect information on advertising exposures. However, translating this seemingly rich into measures of response has proven difficult, largely because concerns that advertisers target customers with a higher propensity buy or increase during periods peak demand. We show how problem can be addressed by studying setting where firm randomly held out from each campaign, creating sequence randomized field experiments mitigates (many)...
Discrete choice models estimated using hypothetical choices made in a survey setting (i.e., experiments) are widely used to estimate the importance of product attributes order make design and marketing mix decisions. Choice experiments allow researcher preferences for features that do not yet exist market. However, parameters from experimental data often show marked inconsistencies with those inferred market, reducing their usefulness forecasting decision making. We propose an approach...
We reframe A/B testing as a decision problem with the goal of maximizing profit and derive optimal sample size formula.
Retail media, where retailers allow brands to promote their products shoppers for a fee, is rapidly growing segment of the advertising industry. As more adopt this model, face decision whether allocate marketing budgets these emerging channels. Our study demonstrates that brand equity plays moderating role in impact retail media on product sales. We develop and estimate dynamic linear model predicts weekly UPC-level sales, enabling us examine how brand-level strengthens and, turn, enhances...
Ad exchanges, where real-time auctions for display ad impressions take place, have historically emphasized user targeting, and advertisers sometimes did not know on which sites their ads would appear; in other words, they had no context. More recently, some exchanges been encouraging publishers to provide context information buyers that allow them adjust bids at specific sites. This article explores the empirical effect of a change provided by private European exchange. Analyzing this as...
As firms collect greater amounts of data about their customers from an ever broader set “touchpoints,” a new methodological challenges arises. Companies often these various platforms at differing levels aggregation, and it is not clear how to merge sources draw meaningful inferences customer-level behavior patterns. In this article, the authors provide method that can use, based on readily available data, gauge monitor multiplatform media usage. The key innovation in Bayesian data-fusion...
A method is proposed to compute more precise standard errors for marketing A/B tests.
This paper characterizes the features of an account-based payment card--including bank debit cards, prepaid and payroll cards--that elicit a high take-rate among low- moderate-income (LMI) households, particularly those without accounts. We apply marketing research techniques, specifically choice modeling, to identify design specific financial services product for LMI who often face difficulties maintaining standard accounts but need banking services. After monthly cost, we find that, on...
Targeting individual consumers has become a hallmark of direct and digital marketing, particularly as it easier to identify customers they interact repeatedly with company. However, across wide variety contexts tracking technologies, companies find that can not be consistently identified which leads substantial fraction anonymous visits in any CRM database. We develop Bayesian imputation approach allows us probabilistically assign sessions users, while ac- counting for customer’s demographic...
Advances in data collection have made it increasingly easy to collect information on advertising exposures.