Research

My research investigates economic phenomena in the digital economy. I do so using novel big data sources and applying modern statistical methods.

On this site, you will find a summary of my current research projects, grouped by publications and working papers.

Table of Contents

Publications

  1. Jürgensmeier, Lukas and Bernd Skiera (2024), “Generative AI for Scalable Feedback to Multimodal Exercises,” International Journal of Research in Marketing, forthcoming, https://doi.org/10.1016/j.ijresmar.2024.05.005.

  2. Proffen, Celina and Lukas Jürgensmeier (2024), “Do political conflicts influence daily consumption choices? Evidence from US-China relations,” Journal of Economic Behavior & Organization, 220, pp. 660-674, https://doi.org/10.1016/j.jebo.2024.02.031, shared first authorship.

  3. Jürgensmeier, Lukas, Jan Bischoff, and Bernd Skiera (2024), “Opportunities for Self-Preferencing in International Online Marketplaces”, International Marketing Review, forthcoming.

  4. Skiera, Bernd and Lukas Jürgensmeier (2024), “Teaching Marketing Analytics: A Pricing Case Study for Quantitative and Substantive Marketing Skills,” Journal of Marketing Analytics, forthcoming, https://doi.org/10.1057/s41270-024-00313-2.

  5. Schönborn, Sofie, Lukas Jürgensmeier, Carolin Neumann, Stefan Hildebrand, Gabriel Häusler, David Middelbeck (2023): “Wind of Change: Ehrenamtliche Organisationen und Angebote der jungen Generation zur Digitalbildung in Deutschland,” in: Digitalisierung in der Hochschullehre: Perspektiven und Gestaltungsoptionen, Forum Lehrerinnen- und Lehrerbildung (11). University of Bamberg Press, https://doi.org/10.20378/irb-59190.

Working Papers

  1. Jürgensmeier, Lukas and Bernd Skiera (2024), “Measuring Self-preferencing on Digital Platforms,” working paper available at SSRN (third-round revise-and-resubmit at the Journal of Marketing).

  2. Lukas Jürgensmeier (2024): “keepar: An R Package to Identify, Acquire, and Transform Online Marketplace Data for Social Science Research,” package available on GitHub.

Detailed Information on Publications

Generative AI for Scalable Feedback to Multimodal Exercises

Jürgensmeier, Lukas and Bernd Skiera (2024), “Generative AI for Scalable Feedback to Multimodal Exercises,” International Journal of Research in Marketing, forthcoming, https://doi.org/10.1016/j.ijresmar.2024.05.005.

Abstract

Detailed feedback on exercises helps learners become proficient but is time-consuming for educators and, thus, hardly scalable. This manuscript evaluates how well Generative Artificial Intelligence (AI) provides automated feedback on complex multimodal exercises requiring coding, statistics, and economic reasoning. Besides providing this technology through an easily accessible web application, this article evaluates the technology’s performance by comparing the quantitative feedback (i.e., points achieved) from Generative AI models with human expert feedback for 4,349 solutions to marketing analytics exercises. The results show that automated feedback produced by Generative AI (GPT-4) provides almost unbiased evaluations while correlating highly with (r = 0.94) and deviating only 6 % from human evaluations. GPT-4 performs best among seven Generative AI models, albeit at the highest cost. Comparing the models’ performance with costs shows that GPT-4, Mistral Large, Claude 3 Opus, and Gemini 1.0 Pro dominate three other Generative AI models (Claude 3 Sonnet, GPT-3.5, and Gemini 1.5 Pro). Expert assessment of the qualitative feedback (i.e., the AI’s textual response) indicates that it is mostly correct, sufficient, and appropriate for learners. A survey of marketing analytics learners shows that they highly recommend the app and its Generative AI feedback. An advantage of the app is its subject-agnosticism—it does not require any subject- or exercise-specific training. Thus, it is immediately usable for new exercises in marketing analytics and other subjects.

Keywords: Generative AI, Automated Feedback, App, Marketing Analytics, Learning.

Do Political Conflicts Influence Daily Consumption Choices? Evidence from US-China Relations

Proffen, Celina and Lukas Jürgensmeier (2024), “Do political conflicts influence daily consumption choices? Evidence from US-China relations,” Journal of Economic Behavior & Organization, 220, pp. 660-674, https://doi.org/10.1016/j.jebo.2024.02.031, shared first authorship.

Abstract

Does political conflict with another country influence domestic consumers’ daily consumption choices? We exploit the volatile US-China relations in 2018 and 2019 to analyze whether US consumers reduce their visits to Chinese restaurants when bilateral relations deteriorate. We measure the degree of political conflict through negativity in media reports and rely on smartphone location data to measure daily visits to over 190,000 US restaurants. A deterioration in US-China relations induces a significant decline in visits not only to Chinese but also to other foreign ethnic restaurants, while visits to typical American restaurants increase. We identify consumers’ age, race, and cultural openness to moderate the strength of this ethnocentric effect.

Keywords: Political conflict, Consumption, Boycotts, Ethnocentrism

Opportunities for Self-Preferencing in International Online Marketplaces

Jürgensmeier, Lukas, Jan Bischoff, and Bernd Skiera (2024), “Opportunities for Self-Preferencing in International Online Marketplaces”, International Marketing Review, forthcoming.

Abstract

Large digital platforms face intense scrutiny over self-preferencing, which involves a platform provider favoring its own offers over those of competitors. In online marketplaces, also called retail or e-commerce platforms, much of the academic and regulatory debate focuses on determining whether the marketplace provider gives preference to its own private labels, such as “Amazon Basics” or Walmart’s “Great Value” products. However, we outline, both conceptually and empirically, that self-preferencing can also occur through other dimensions of vertical integration—namely, retailing and fulfillment. This article contributes by conceptualizing three dimensions of vertical integration in online marketplaces—private labels, retailing, and fulfillment. Then, two studies empirically assess (i) which of the 20 most-visited global online marketplaces vertically integrate which dimension and (ii) which share of 600 million available offers are vertically integrated to which degree in eleven international Amazon marketplaces. The majority of the leading marketplaces vertically integrate all three dimensions, implying ample opportunities for self-preferencing. Across international Amazon marketplaces, only 0.02% of available offers consist of an Amazon private-label product. However, Amazon is a retailer for around 31% and fulfills around 38% of all available offers in its marketplaces. Hence, self-preferencing on Amazon can occur most frequently through retailing and fulfillment but comparatively infrequently through private-label offers. Still, these shares differ substantially by country—every second offer is vertically integrated in the US, but only one in ten in India. Most of the self-preferencing debate often focuses on private-label products. Instead, we present large-scale empirical results showing that self-preferencing on Amazon could occur most often through retailing and fulfillment because these channels affect much larger shares of offers. We also measure the variation of these shares across countries and relate them to regulatory environments.

Teaching Marketing Analytics: A Pricing Case Study for Quantitative and Substantive Marketing Skills

Skiera, Bernd and Lukas Jürgensmeier (2024), “Teaching Marketing Analytics: A Pricing Case Study for Quantitative and Substantive Marketing Skills,” Journal of Marketing Analytics, forthcoming, https://doi.org/10.1057/s41270-024-00313-2.

The case study, solution, and data is available through GitHub.

Abstract

This article describes a data-driven case study for teaching and assessing students’ skills in marketing analytics, specifically in pricing. This case study combines teaching econometrics to analyze data and substantive marketing to derive managerial insights. The econometric challenge requires students to set up and implement a regression analysis to derive the demand function, detect multicollinearity, and select appropriate data visualizations. The substantive challenge requires deriving optimal pricing decisions and understanding how the parameters of the demand function impact optimal prices and the associated profit. We test the case study in a marketing analytics exam and discuss the performance of 134 students. Beyond assessing student performance in an exam, the case study facilitates teaching through in-class group work or assignments. Free of charge, under a liberal CC BY license, we encourage other educators to use the case study in their teaching. We provide the necessary data and a sample solution using the statistical programming language R.

Keywords: Marketing Analytics, Pricing, Teaching, Education, Case Study, Data Science

Non-Profit Organizations and their Offers for Digital Education in Germany

Schönborn, Sofie, Lukas Jürgensmeier, Carolin Neumann, Stefan Hildebrand, Gabriel Häusler, David Middelbeck (2023): “Wind of Change: Ehrenamtliche Organisationen und Angebote der jungen Generation zur Digitalbildung in Deutschland,” in: Digitalisierung in der Hochschullehre: Perspektiven und Gestaltungsoptionen, Forum Lehrerinnen- und Lehrerbildung (11). University of Bamberg Press, https://doi.org/10.20378/irb-59190.

Abstract

In addition to traditional educational institutions, volunteer organizations play an important role, especially in digital education. This article shows which volunteer-organized offerings exist in Germany, discusses the innovative concepts behind them, and illustrates how traditional educational institutions can learn from this volunteer engagement. To this end, the authors present the results of a survey of 19 organizations and two exemplary projects in case studies, and recommend three concrete actions for education policy based on these results.

Keywords: Digital Education; Volunteering; Blended Learning; Peer Learning; Coding; Survey

Detailed Information on Working Papers

Measuring Self-Preferencing on Digital Platforms

Authors: Lukas Jürgensmeier and Bernd Skiera.

Status: Under third-round review at the Journal of Marketing.

Read the full working paper on SSRN.

Abstract

Digital platforms use recommendations to facilitate exchanges between platform actors, such as trade between buyers and sellers. Aiming to protect consumers and guarantee fair competition on platforms, legislators increasingly require that recommendations on market-dominating platforms be free from self-preferencing. That is, platforms that also act as sellers (e.g., Amazon) or information providers (e.g., Google) must not prefer their own offers over comparable third-party offers. Yet, successful enforcement of self-preferencing bans—to the potential benefit of consumers and third-party actors—requires defining and measuring self-preferencing across a platform. In the context of recommendations through search results, this research contributes by i) conceptualizing a “recommendation” as an offer’s level of search engine visibility across an entire platform (instead of its position in specific search queries, as in previous research); ii) discussing two tests for self-preferencing, and iii) implementing them in two empirical studies across three international Amazon marketplaces. Contrary to consumer expectations and emerging literature, our analysis finds almost no evidence for self-preferencing. A survey reveals that even if Amazon were proven to engage in self-preferencing, most consumers would not change their shopping behavior on the platform—highlighting Amazon’s significant market power and suggesting the need for robust protections for sellers and consumers.

Keywords: Digital Platforms, Amazon, Competition, Antitrust, Search Engines, Digital Markets Act, American Innovation and Choice Online Act.

keepar: An R Package to Identify, Acquire, and Transform Online Marketplace Data for Social Science Research

Authors: Lukas Jürgensmeier

Status: Package available at GitHub; draft working paper available upon request.

Abstract

Researchers frequently use online marketplace data for social science research. However, obtaining and processing such data is cumbersome, and either involves web scraping or access to a pre-existing database. One such a database is the commercial data provider Keepa.com, which tracks Amazon products over time. While such database is accessible via API, identifying and processing the relevant data—into a suitable format for social science research—requires significant effort. This article introduces the keepar package, an R package designed to simplify this data acquisition and transformation process. Through an illustrative research project analyzing the market for rubber ducks on Amazon, this article explains how to use the package to obtain and transform the Keepa.com data. Making this package available open source, this article contributes to making this data source more widely available to social science researchers.