About

Michel Wedel is a Distinguished University Professor and holds the PepsiCo Chair in Consumer Science at the Robert H. Smith School of Business, University of Maryland. His main research interest is in consumer science, focusing on the application of statistical and econometric methods to enhance the understanding of consumer behavior and improve marketing decision-making. Much of his recent work involves measuring the effectiveness of visual marketing using eye-tracking technology. He teaches models for marketing decision-making for MBA students and advanced marketing analytics for MS students. Wedel has an extensive academic background with a PhD in Marketing from the University of Wageningen, NL, and multiple master's degrees in Statistics, Biomathematics, and Business Management from Dutch institutions. He has been recognized with numerous awards and honors, including the Lifetime Achievement Awards from the American Marketing Association and the University of Groningen, as well as the prestigious Robert J. Lavidge Global Marketing Research Award and the Charles C. Parlin award for outstanding contributions to marketing research. He has held visiting and affiliate positions at various international institutions and is a Fellow of INFORMS, the American Statistical Association, and the American Marketing Association. His research expertise encompasses marketing research methodology, statistical and econometric modeling of consumer behaviors, and the integration of behavioral and managerial aspects in marketing. He has developed statistical models that represent consumer psychological mechanisms and behaviors, with a particular interest in Bayesian statistics to facilitate better decision-making in applied marketing settings. His work also includes eye-tracking and visual marketing, leveraging large-scale eye-tracking data to analyze consumer attention and neuropsychological theories within statistical models.

Research topics

• Computer Science
• Business
• Marketing
• Sociology
• Psychology
• Economics
• Data science
• Management science
• Human–computer interaction

Selected publications

• AdGazer: Improving Contextual Advertising with Theory-Informed Machine Learning

  Journal of Marketing · 2025-11-02

  articleOpen access

  Contextual advertising involves matching features of ads to features of the media context where they appear. The authors propose AdGazer, a new machine learning procedure to support contextual advertising. It comprises a theoretical framework organizing high- and low-level features of ads and contexts, feature engineering models grounded in this framework, an XGBoost model predicting ad and brand attention, and an algorithm optimally assigning ads to contexts. AdGazer includes a multimodal large language model to extract high-level topics predicting the ad–context match. This research uses a unique eye-tracking database containing 3,531 digital display ads and their contexts, and aggregate ad and brand gaze times. The authors compare AdGazer’s predictive performance with that of two feature learning models, VGG16 and ResNet50. AdGazer predicts highly accurately with holdout correlations of .83 for ad gaze and .80 for brand gaze, outperforming both feature learning models and generalizing better to out-of-distribution ads. Context features jointly contributed at least 33% to predicted ad gaze and about 20% to predicted brand gaze, good news for managers practicing or considering contextual advertising. The authors demonstrate that the theory-informed AdGazer effectively matches ads to advertising vehicles and their contexts, optimizing ad gaze more than current practice and alternatives like text-based and native contextual advertising.

  PublisherOA PDFDOI

• IPGO: Indirect Prompt Gradient Optimization for Parameter-Efficient Prompt-level Fine-Tuning on Text-to-Image Models

  ArXiv.org · 2025-03-25

  preprintOpen access

  Text-to-Image Diffusion models excel at generating images from text prompts but often exhibit suboptimal alignment with content semantics, aesthetics, and human preferences. To address these limitations, this study proposes a novel parameter-efficient framework, Indirect Prompt Gradient Optimization (IPGO), for prompt-level diffusion model fine-tuning. IPGO enhances prompt embeddings by injecting continuously differentiable embeddings at the beginning and end of the prompt embeddings, leveraging low-rank structures with the flexibility and nonlinearity from rotations. This approach enables gradient-based optimization of injected embeddings under range, orthonormality, and conformity constraints, effectively narrowing the search space, promoting a stable solution, and ensuring alignment between the embeddings of the injected embeddings and the original prompt. Its extension IPGO+ adds a parameter-free cross-attention mechanism on the prompt embedding to enforce dependencies between the original prompt and the inserted embeddings. We conduct extensive evaluations through prompt-wise (IPGO) and prompt-batch (IPGO+) training using three reward models of image aesthetics, image-text alignment, and human preferences across three datasets of varying complexity. The results show that IPGO consistently outperforms SOTA benchmarks, including stable diffusion v1.5 with raw prompts, text-embedding-based methods (TextCraftor), training-based methods (DRaFT and DDPO), and training-free methods (DPO-Diffusion, Promptist, and ChatGPT-4o). Specifically, IPGO achieves a win-rate exceeding 99% in prompt-wise learning, and IPGO+ achieves a comparable, but often better performance against current SOTAs (a 75% win rate) in prompt-batch learning. Moreover, we illustrate IPGO's generalizability and its capability to significantly enhance image quality while requiring minimal data and resources.

  PublisherOA PDFDOI

• How to Conduct Valuable Marketing Research With Neurophysiological Tools

  Psychology and Marketing · 2025-07-19 · 9 citations

  articleOpen accessSenior author

  ABSTRACT Consumer neuroscience is gaining attention in the marketing field. The growing interest calls for a framework integrating neuroscience in marketing. This paper aims to serve as a practical guide for conducting consumer research using neurophysiological tools. The paper is organized into three main sections. The first section presents a framework for categorizing types of consumer neuroscience research based on four primary research objectives. The following section describes the use of neurophysiological tools in marketing and addresses their roots in their mother disciplines. Specifically, we address electrocardiography, galvanic skin conductance, eye‐tracking, electroencephalography, functional magnetic resonance imaging, and functional near‐infrared spectroscopy. Additionally, we refer to emerging measurements from hormones and genes. Likewise, this section highlights the most influential papers, equipment facilities, and software on each tool to support researchers who need to become more familiar with any of those techniques. Third, this paper introduces an integrative framework for consumer neuroscience research in marketing, covering research aims, types of stimuli, changes in organisms, and consumer response processes. In addition to core neuroscience citations, the paper incorporates specific marketing‐relevant consumer neuroscience papers to guide research in the marketing field.

  PublisherOA PDFDOI

• Effects of advertising exposure duration and frequency: a theory and initial test

  Journal of Marketing Analytics · 2025-02-01 · 2 citations

  articleSenior authorCorresponding
  PublisherDOI

• SIGN: A Statistically-Informed Gaze Network for Gaze Time Prediction

  ArXiv.org · 2025-01-29

  preprintOpen accessSenior author

  We propose a first version of SIGN, a Statistically-Informed Gaze Network, to predict aggregate gaze times on images. We develop a foundational statistical model for which we derive a deep learning implementation involving CNNs and Visual Transformers, which enables the prediction of overall gaze times. The model enables us to derive from the aggregate gaze times the underlying gaze pattern as a probability map over all regions in the image, where each region's probability represents the likelihood of being gazed at across all possible scan-paths. We test SIGN's performance on AdGaze3500, a dataset of images of ads with aggregate gaze times, and on COCO-Search18, a dataset with individual-level fixation patterns collected during search. We demonstrate that SIGN (1) improves gaze duration prediction significantly over state-of-the-art deep learning benchmarks on both datasets, and (2) can deliver plausible gaze patterns that correspond to empirical fixation patterns in COCO-Search18. These results suggest that the first version of SIGN holds promise for gaze-time predictions and deserves further development.

  PublisherOA PDFDOI

• Contextual Advertising with Theory-Informed Machine Learning

  SSRN Electronic Journal · 2024-01-01

  preprintOpen access
  PublisherDOI

• Bayesian analysis of experimental and observational data: a review and illustration of the BANOVA R package

  Journal of Marketing Analytics · 2024-05-11

  review1st authorCorresponding
  PublisherDOI

• Predicting and optimizing marketing performance in dynamic markets

  OR Spectrum · 2024-02-29 · 7 citations

  articleOpen accessSenior authorCorresponding

  Abstract Our world is turbulent: ecological, social, political, technological, economic, and competitive business environments change constantly. Consumers have changing preferences, learn, build trust in brands, adopt new products, and are persuaded by advertising. Firms innovate and engage in and respond to competition. Exogenous events, such as changes in economic conditions and regulations, as well as human crises, also cause major shifts in markets. This special issue focuses on novel Marketing data and modern methodologies from different fields (e.g., Operations Research (OR), Statistics, Econometrics, and Computer Science), which help firms understand, utilize, and respond to market dynamics more efficiently. Here we propose a framework comprising analytical methods and data for dynamic markets that is useful for structuring research in this domain. Next, we summarize the history of the Marketing/OR interface. We highlight studies at the Marketing/OR interface from the last decade focusing specifically on dynamic markets and use our proposed framework to identify trends and gaps in the extant literature. After that, we present and summarize the papers of the current special issue and their contributions to the field against the backdrop of our framework and the trends in the literature. Finally, we conclude and discuss which future Marketing/OR research could tackle important issues in dynamic markets.

  PublisherOA PDFDOI

• The Impact of App Crashes on Consumer Engagement

  Journal of Marketing · 2024-11-22 · 1 citations

  articleSenior author

  The authors develop and test a theoretical framework to examine the impact of app crashes on app engagement. The framework predicts that consumers increase engagement after encountering a single crash due to their need for closure and their curiosity, yet reduce engagement after experiencing repeated and concentrated crashes, primarily because of frustration and perceived task unattainability; the recency of crashes moderates these effects. Field data analysis reveals that while a crash truncates a session and reduces content consumption, it increases page views in the following session. However, this increase in page views does not compensate for the loss during the crashed session. Frequent and more concentrated crashes curtail engagement. Three experiments in which crashes are exogenously manipulated in a different context support the validity and generalizability of these findings, confirm the proposed mediators, and demonstrate how to lessen the negative impact of repeated crashes with postcrash messages. The research adds new dimensions to the task pursuit literature and provides managers with a framework to quantify the economic impact of crashes, analyze content substitution behavior, and assess the bias of a transactional view of crash incidents. Additionally, it offers insights into targeted release of features to more tolerant users and strategic design of postcrash messages.

  PublisherDOI

• Polytomous IRT Models With A Cut-Point Formation Mechanism: An Application To The Measurement of Anxiety

  SSRN Electronic Journal · 2023-01-01

  articleOpen accessSenior author
  PublisherDOI

Frequent coauthors

• Wagner A. Kamakura

  Rice University

  89 shared

• Rik Pieters

  Tilburg University

  83 shared

• Wayne S. DeSarbo

  Park University

  45 shared

• Dick R. Wittink

  36 shared

• Ralf van der Lans

  32 shared

• Peter S. H. Leeflang

  Universidade Nova de Lisboa

  24 shared

• Frenkel Ter Hofstede

  22 shared

• Philippe A. Naert

  20 shared

Awards & honors

• Paul D. Converse Award for pioneering in developing the theo…
• Ubbo Emmius Medal for Scientific Achievements, University of…
• Robert J. Lavidge Global Marketing Research Award, American…
• Buck Weaver Award for excellence in the achievement of rigor…
• Irwin/McGraw-Hill Distinguished Marketing Educator award, Am…