With our research, we strive to make a significant contribution to the development of the marketing discipline. We have a strong empirical research tradition and typically employ advanced management and marketing science methods to provide decision support for issues of managerial relevance. As the world is not neatly compartmentalized into single-problem questions, much of our research requires collaboration across disciplinary borders.
Prior research findings have been published in highly-reputed journals including Marketing Science, Journal of Marketing, International Journal of Reserach in Marketing (IJRM), Journal of Interactive Marketing, Decision Support Systems, or the European Journal of Operational Research (EJOR).
(c) Lana Lauren
Martin Reisenbichler, Thomas Reutterer, David Schweidel and Daniel Dan (2022), "Frontiers: Supporting Content Marketing with Natural Language Generation", Marketing Science, 41(3), 441–452.
(c) Lana Lauren
Jan Valendin, Thomas Reutterer, Michael Platzer and Klaudius Kalcher (2022), "Customer base analysis with recurrent neural networks", International Journal of Research in Marketing 39 (2022) 988-1018.
(c) Lana Lauren
Thomas Reutterer, Michael Platzer and Nadine Schröder (2021), "Leveraging purchase regularity of predicting customer behavior the easy way", International Journal of Research in Marketing 38 (2021) 194-215.
Current Research Topics
Work conducted by the Institute members covers a broad spectrum of research topics. The following is a brief selection of the major topics under investigation at the Institute:
CUSTOMER RELATIONSHIP MANAGEMENT (CRM)
In this research area we are particularly interested in studying and forecasting the dynamics in evolving customer-firm relationships using advanced statistical methodology and machine learning models. In a multi-product company context (e.g., in retailing), we investigate the role of specific products (categories) in attracting „valuable“ customer groups who previously made purchases outside the focal firm. Another important stream of research aims to leverage regularities in past transaction timings to improve predictions of future customer behavior.
SEARCH ENGINE OPTIMIZED CONTENT MARKETING
In this field of research we investigate how advances in natural llanguage generation (NLG) can support content marketing to draft website content in a search engine optimized way. Using a series of studies we examine how semi-automated, NLG model based content writing performs relative to SEO content provided by experts. We also study applications to search engine advertising and explore how to incorporate brand-specific context information in machine-generated marketing content.
CUSTOMER ANALYTICS IN DATA RICH ENVIRONMENTS
The key drivers in this research area are recent advances in information technology and their impact on how consumers gather information, make decisions, and interact with organizations. Using sentiment analysis and text-mining technologies, we analyze user-generated content to derive new insights for marketing decision makers. Online customer reviews represent such a typical source of information which can be lerveraged to engage into conversations with a firm's customer base and to improve service quality and to cultivate customer loyalty.
MARKETING SCIENCE METHODS
In interdisciplinary teams we aim to develop, adopt and empirically test the performance of newly emerging analytical, computationally intense methodology and/or modeling approaches to marketing problems. Selected areas of interest include the application of model-based clustering, psychometric methods, or deep learning methods in the field of marketing.