I am a doctoral candidate in Marketing at Goethe University Frankfurt supervised by Bernd Skiera. In Fall 2018 and Spring 2019 I was a visiting doctoral scholar at the Univerity of North Carolina (UNC) at Chapel Hill, USA, invited by my co-supervisor Daniel M. Ringel.
My research studies contemporary marketing problems via the lens of modern data science. In particular, I investigate the relationships among market actors, such as competing firms, consumers with similar behavior, or consumer-brand interactions. I believe that understanding these relationships can provide novel solutions to practical marketing challenges, such as competitive analysis, branding, positioning, or targeting.
A centerpiece of my work is dynamic mapping which I use to investigate positioning dynamics among firms, political parties or media outlets.
I am on the Summer/Fall 2022 academic job market.
Dr. Marketing, 2023 (expected)
Goethe University Frankfurt (Germany)
M.Sc. Money & Finance (Financial Economics), 2017
Goethe University Frankfurt (Germany)
B.Sc. Mathematics and Economics, 2015
University of Wuerzburg (Germany)
Forthcoming in Marketing Science
Abstract: A common element of market structure analysis is the spatial representation of firms’ competitive positions on maps. Such maps typically capture static snapshots in time. Yet, competitive positions tend to flux, and market structures can evolve. Embedded in the evolution of market structures are firms’ trajectories—the series of changes in firms’ positions over time relative to all other firms in a market. Identifying these trajectories contributes additional insight to market structure analysis because trajectories reveal firms’ (re)positioning strategies, identify emerging threats and opportunities, and provide a forward-looking perspective on competition. To unlock these insights, we propose EvoMap, a novel dynamic mapping framework that identifies firms’ trajectories from high-frequency and potentially noisy data. We validate EvoMap in an extensive simulation study and show that it outperforms alternative approaches for mapping market structure evolution. Using EvoMap, we study the trajectories of more than 1,000 publicly listed firms over the course of 20 years based on similarities in their 10-K product descriptions. We find major changes in several firms’ positioning strategies, including Apple, Walmart, and Capital One. Because EvoMap accommodates a wide range of mapping methods, analysts can easily apply it in other empirical settings and to data from various sources.
New version available soon
Abstract: Like brands, political parties must position themselves against their competitors to capture market share, that is, votes. Likewise, these positions are not static but rather frequently change in response to external events or shifts in public sentiment. Understanding when/how such changes in party positioning occur and how they relate to voter support can provide campaign managers with valuable insights for their positioning or branding strategies. Despite this relevance, marketing research has mainly developed approaches for studying brand positioning and given little attention to political parties. To fill this gap, we introduce an approach for estimating high-frequency time series of party positions from textual data. Our approach leverages recent innovations from natural language processing and market structure analysis (transformer models and dynamic mapping). We apply our approach to thousands of parliamentary speeches in Germany over 24 years and use these estimates to quantify party positioning along various dimensions, such as their temporal consistency or degree of differentiation. Our text-based estimates uncover multiple significant shifts in Germany’s political landscape, such as the con-/divergence of competing parties. We show that these shifts in party positioning can substantially help to predict shifts in voter support, measured via weekly election polls, above and beyond established indicators.
Job Market Paper
Abstract: Consumers routinely use search engines like Google to satisfy their information needs. These searches provide brands with ample opportunity to connect with consumers. Yet, brands first need to understand their target consumers’ information needs to create relevant content or target them via ads. Yet, identifying consumers’ information needs is challenging, as consumers’ online searches are typically not observable to brands. This article provides a new approach to identifying consumers’ information needs. Our approach tracks consumers’ search behavior via a custom-developed search simulator and uses textual data analysis to infer consumers’ information needs from the recorded search queries. We apply our approach to identify consumers’ information needs when searching for a new credit card. Our analysis reveals eleven broad information needs, including information on benefits, costs and fees, interest rates, specific brands, or traveling. These insights helped our practice partner target consumers who generated 10,000s of additional monthly clicks at below-average ad prices.
developed to disseminate my work
A comprehensive Python toolbox for mapping evolving relationship data
evomap
allows users to create spatial representations (‘maps’) based on data capturing actors' evolving relationships. In Marketing, such maps are typically used to analyze the competitive positions within a market (so-called market structure analysis). There, data can originate from surveys, clickstreams, text-mining, embeddings, or many others. Beyond Marketing, such maps can be used to study different kinds of networks (e.g., social, economic, or financial networks), political ideology, or act as a general tool for dimensionality reduction. In many cases, such data is nowadays available longitudinally, i.e., for multiple subsequent points in time. evomap
allows users to preprocess such data efficiently, implements muliple (static and dynamic) mapping methods from Psychometrics and Computer Science, and provides users with an easy-to-use API to explore the results.
On the technical side, evomap
is an independent Python package, easily compatible with other data science pipelines (such as scikit-learn
), and implements runtime optimization via C.
`evomap` is based on my dissertational research on dynamic mapping, and currently supports ongoing research projects, industry applications, and teaching in marketing analytics.
A first pre-release version is available via GitHub (soon on PyPi!). For more details, read the docs or visit this tutorial.
Courses in which I was co-instructor or teaching assistant
Role: Co-instructor with Martin Schmidberger (Winter 2021).
Bachelor Seminar covering advanced marketing analytics techniques (e.g., prediction, logfile analysis, or text mining) and their practical application to real-world customer data.
Evaluation: 5.6/6
Role: Teaching assistant for Bernd Skiera (Fall 2017 - Summer 2021).
Bachelor Course covering common marketing analytics techniques (e.g., regression, conjoint, clustering, perceptual mapping), applications to real-world data and a R/RStudio-based final exam.
Role: Co-instructor with Martin Schmidberger (Summer 2022).
Master Seminar focused on predictive modeling in Marketing. Covers the application of modern machine learning algorithms for predicting customers' purchase behavior and optimizing the efficiency of marketing campaigns.
Evaluation: 5.7/6