top of page

Professor of Marketing 

Imperial College Business School

South Kensington Campus                               

London SW7 2AZ

Faculty Profile Page


Google Scholar profile

SSRN profile

LinkedIn profile  


I use data to understand how consumers make choices in settings

ranging from laundry detergent discounts to choosing a hospital for

a bypass operation. I am particularly interested in how consumers gather

information before making a purchase and what we can learn from data on

consumer search behavior.

I am an Associate Editor at Marketing Science, Quantitative Marketing and Economics,

and the Journal of  Industrial Economics. I co-organize the European Quant Marketing Seminar (eQMS),

and I am a Public Editor at @QME_Journal.



Recent Research Highlights:


🚨🚨 New Working Paper: 🚨🚨 Demand Estimation with Text and Image Data 👈👈

New machine learning tools allow researchers to process unstructured data from text and images

more easily. In this new paper with Giovanni Compiani and Ilya Morozov, we extract measures of

similarity between products from product images and different sources of text (product descriptions,

reviews, etc.) and then feed them into a demand model so that higher similarity leads to larger

cross-price elasticities between products. We apply the model to data form multiple categories and

show that it helps us recover flexible substitution patterns.

Paper on Soda Taxes featured on the "How I Wrote This" podcast.

Our paper on soda taxes (with Anna Tuchman and Song Yao was covered in the most recent

episode  of the “How I Wrote This” podcast.  We discuss what motivated us to pursue this research,

the various  decisions that we took when working  on the paper, and how we navigated the review process. 

For a short summary of the paper, check out the video posted on the right ... 

The Sequential Search Model: A Framework for Empirical Research (with Accompanying Code)

The sequential search model (Weitzman, 1979) has emerged as the workhorse model for research based on

consumer search data. Papers in this growing literature adopt different specifications of utility, estimate

the model using a variety of approaches, and discuss identification in relation to a specific setting. Our aim

in this paper (joint work with Elisabeth Honka and Raluca Ursu) is to provide a unified treatment of the

aspects of the sequential model that are relevant to empirical work in order to consolidate knowledge and

to provide a comprehensive introduction on the use of the sequential model, especially for researchers that

are new to working with search data and models.

We also provide a comprehensive code base that covers different methods for computing reservation utilities

and 4 different estimation approaches. Click here for access to the code.

Machine Learning and Targeted Marketing

Machine learning methods are increasingly used to design personalized marketing strategies such as targeted

coupons and personalized advertising messages. In a recent talk at the 2023 Katia Campo symposium, I talked

about what I see as three important ingredients to designing targeting strategies: 

(1) the importance of incremental targeting (i.e. based on treatment effect heterogeneity)

(2) how to derive policies from machine learning estimates by using a decision-theoretic framework

(3) how to compare the performance of ML methods based on the profits that policies derived from a given model


Slide are available here 👉 Katia Campo Price Targeting Slide-deck.

Find out more about my recent research projects on my Blog.

... or follow me on Twitter ... 

Professor Stephan Seiler
bottom of page