Marketing Modeling
The rapid growth of digital and other forms of marketing data creates unprecedented opportunities to understand markets, predict customer behavior, evaluate marketing effectiveness, and improve marketing decisions. Researchers in the Marketing Modeling group combine marketing analytics, artificial intelligence, and econometric modeling to address these opportunities.
Our research is predominantly empirical and addresses substantive marketing questions using methods from econometrics, statistics, data science, machine learning, psychometrics, and operations research, often in collaboration with researchers in Consumer Behavior and Marketing Strategy. We work with a wide range of real-world data, including customer, scanner and panel data, digital and social media data, longitudinal and time-series data, network data, and large-scale datasets from companies and public organizations, including member companies of the Customer Insights Center. Across these areas, our models can serve three complementary purposes: describing marketing phenomena; predicting customer and market developments; and prescribing actions that can improve marketing decisions.
Marketing effectiveness, market dynamics, and generalizations
Research examines when and how marketing strategies create value and how their effectiveness changes over time, and across customers, firms, and market environments. Topics include advertising and communication, pricing and promotions, customer acquisition and retention, competitive dynamics, crises and external shocks, and short- versus long-term marketing effectiveness. Meta-analytic research integrates findings across studies and contexts to identify generalizable marketing effects and the conditions under which they vary.
Digital marketing, AI, and marketing analytics
Digitalization has created new marketing environments, new forms of data, and new opportunities for marketing decision-making. We investigate digital advertising, e-commerce, platforms and social media, including social networks, word of mouth, and social influence. Using artificial intelligence and machine learning methods, we consider how these technologies can improve marketing decisions and how their use affects customers, firms, and society.
Customer analytics and relationship management
We use customer-level data to understand and predict customer behavior and support managerial decision-making, also in high-stakes environments such as blood donations. Topics include customer acquisition and retention, churn, customer lifetime value, loyalty and engagement, product returns, targeting, and personalized marketing.
Methodological innovation
An important part of our research involves developing and advancing quantitative methods for marketing. Our expertise includes econometric and time-series modeling, state-space models, mixture and choice models, meta-analysis, causal inference, machine learning, and artificial intelligence, including generative AI and large language models. We apply these methods to structured and unstructured data, including text, network, and other complex data, and develop approaches for prediction and decision support.
Researchers contributing to this theme include:
Edlira Shehu, Jaap Wieringa, Tammo Bijmolt, Maarten Gijsenberg, Hans Risselada, Roelof Hars, Corine Noordhoff.