There are increasing demands for "causal ML models" of the agent behaviors, which enable us to unbox the complex black-box models and make inferences or do proper counterfactual simulations. Many applications (especially in Marketing) intrinsically call for measurement of the causal impact of the product, pricing, and promotion decisions beyond predictions, either from observational data or combinations of experimental and observational data.
Discrete choice modeling of agent behaviors is a generative modeling framework, created by an Economist, Daniel McFadden (Nobel Prize, 2000). This has been a work-horse model in Economics, Marketing Science, and Operation Research. However, this modeling framework is less known to ML/AI researchers outside of Computational Social Science. In this talk, I will introduce discrete choice models of agent behaviors with a focus on consumer demand modeling. I will talk about two different ways of modeling consumer heterogeneity: discrete vs. continuous. In addition, how this individual-level model (i.e. varying parameters at the individual level) can be estimated by using simulated individuals when you only have aggregate sales data is also discussed. A dynamic version of this model is related to reinforcement learning, and I will discuss this linkage. Finally, an extension of this model to consumer online search behaviors and a neural network representation of discrete choice models will be discussed.
Minha Hwang is a Principal Architect at Microsoft. He is a Marketing Data Scientist, who focuses on causal inference, consumer behaviour modelling, marketing/product impact measurement, and explainable AI (xAI), and prescriptive data science. He likes to explore new and different areas: Double Ph.D. - Marketing Science from UCAL Anderson and Materials Science & Engineering from MIT, former academic now in practice - Former Assistant Professor of Marketing at McGill University in Canada, a management consultant who worked both as a generalist and a specialist, project-based data science role and SaaS Marketing & Sales solution data science role - especially in pricing, promotion ROI, assortment, purchase structure, digital marketing, CRM and CLV. He has published his research and applied works in Marketing Science, Information Systems, Operations Research, Economics, and Applied Physics journals.