Computational Marketing

Computational Marketing Lab

We combine computing, data science, and economics to advance the theory and practice of marketing and to make it effective in technology-driven businesses.

Mission & Leadership

The computational marketing lab brings together affiliated faculty, students, and industry practitioners to collaborate on issues related to computation and data-driven marketing. We develop research that combines data with economics, machine learning, and statistics tools and interprets it through the lens of social science frameworks to answer strategic questions of interest to the organization.

For industry, the collaboration helps to identify durable solutions to marketing issues that embed them within a well-posed societal, economic, competitive, human-centric framework. For academia, the collaboration helps ensure that scholarly research addresses problems that are practically relevant, and that leverages the data, business context, and field-experimentation possibilities provided by industry.

Faculty Director
Harikesh S. Nair
The Jonathan B. Lovelace Professor of Marketing
Strategy & Research

The primary purpose of the lab is to support data-driven, cutting-edge research at the intersection of computational marketing, social science, and business. In addition to facilitating research, the lab invests in disseminating research findings broadly and in generating a productive dialogue between academia and industry by publishing and presenting research at industry and academic conferences and journals, and by hosting events.

A key industry collaborator will be, whose expertise and data assets can be accessed by members of the lab for research.

Featured Research

This paper presents an empirical framework to analyze salesforce compensation. It uses a model built on economic theory and solved using numerical dynamic programming. The model is implemented at a large contact lens manufacturer in the United States to improve salesforce contracts as part of a multimillion-dollar, multi-year collaboration. The improvements resulted in a 9% increase in overall revenues, indicating the success of the field-implementation. The results bear out the face validity of computational economic models for real-world compensation design and marketing decision-making.