Personalization
Personalization
Using Data and AI for the Optimal Personal Experience
With the advent of big data and the machine learning techniques that can analyze these data, there are ever more opportunities for firms to improve their customer experience by providing personalization in a truly (artificially) intelligent manner.
As personalization aims to better meet customer needs, it requires smart, timely, and situation-specific inferences on customer preferences. These inferred preferences can feed directly into automated systems that tailor the offerings to the customers’ needs. Alternatively, interpretable models can be built that provide a dashboard for managers where they can follow the market, segment or individual level needs or a toolbox to support the design of tailor-made activities to meet these needs. Our research focuses both on interpretable inferences to improve human decision making on personalization as well as more complicated, yet less interpretable approaches that personalize the user experience without human intervention or insights.
Research Projects
Personalized product recommendations and personalized assortments
Given the large assortments that are typically encountered at online retailers, customers will benefit tremendously by being given easy access to the most relevant products that the retailer has to offer. We develop machine learning based models to predict the products that are most likely to be purchased by a customer, given the current status in their purchase process.
- Understanding Large-Scale Purchase Behavior, Marketing Science, forthcoming.
- Product set granularity and consumer response to recommendations, Journal of the Academy of Marketing Science, 2020
- Model-Based Predictions for Large Assortments, Marketing Science, 2016
Personalized promotions and product customization
Using scalable modelling approaches, often based on dynamic text analysis methods, we are able to better understand what customers do, but also get a sense of why they do this. Understanding what drives customer behavior provides us with key insights for personalized promotions, where we aim to optimize company actions, e.g. to set a default, suggest a product, to provide a promotion – and what type of promotion then works best, or maybe to do nothing if that is optimal.
Ongoing research of two PhD students
- Preference Dynamics in Sequential Consumer Choice with Defaults, Journal of Marketing Research, 2020
Personalized financial advice
We research the use of rich customer input from newly developed interactive support tools to come to the best, personalized financial advice. Currently, we are applying this in the realm of pension-related decisions through Netspar funded research, jointly with industry partners such as Achmea and ASR.
- Digital customization of consumer investments in multiple funds: virtual integration improves risk–return decisions, Journal of the Academy of Marketing Science, 2020.
- Regulating Robo Advice Across the Financial Services Industry, Iowa Law Review, 2018
- Whose Algorithm Says So: The Relationships Between Type of Firm, Perceptions of Trust and Expertise, and the Acceptance of Financial Robo-Advice, Journal of Interactive Marketing, 2020
