Research
Journal Publications
Measuring Income and Wealth Effects on Private-Label Demand with Matched Administrative Data
with Adrian Fritzsche, Roman Inderst and Thomas Otter
Marketing Science 41(3), 637-656
Abstract: Industry sentiment links income and wealth to private-label demand. The intuition is that decreasing income and wealth increases the demand for (cheaper) private labels. Whereas plausible causality is harder to establish in aggregate time series analyses, such analyses suggest large effect sizes. An individual-level perspective greatly facilitates plausibly causal estimates but poses measurement challenges. We overcome these challenges by linking household scanner data to administrative data. We analyze individual-level private-label shares measured in household scanner data as a function of income and wealth, both from a linked administrative database in the Netherlands in the period from 2011 to 2018 and aggregated over all household members (rather than only from the main earner). We find that relying on within-household variation in surveyed income data significantly attenuates income effects relative to using that from administrative data. Yet, we still find an economically small effect. In addition, changes in wealth have at most an economically small effect on private-label shares.
Working Papers
CPG Consumption in times of recession: Novel evidence from matched administrative data
with Roman Inderst
Revise & Resubmit at Quantitative Marketing and Economics (QME)
This Version: October 2022
Abstract: We exploit a novel data source that combines on the level of individual households administrative income and sociodemographic data from tax records with household scanner data for CPG consumption. We document significant unexplained variation in household expenditures and thereby reveal substantial scope for potential savings. Exploiting considerable within-household variation from the Dutch double-recession in the analysed period from 2011 to 2018, we find only an economically small relationship of expenditure with income, which is also not higher for households with low income or low savings. Albeit still small, the respective coefficient is larger for non-food expenditure, negative income changes, and particularly for single households.
Grocery Shopping under Cognitive Constraints and Restrictive Budget: An Algorithmic Approach
This Version: May 2021
Abstract: This paper presents an algorithmic approach to optimize the grocery shopping behaviour of consumers under specific circumstances: a highly restrictive budget and cognitive constraints. I develop a formal optimization model that accounts for the trade-off between dietary objectives and product preferences during the shopping process. I show how an heuristic algorithm and its implementation in an interactive web platform can be used to find local optima to the consumers' choice problem, by alleviating the burden from limited processing capacity, especially overchoice. The approach presented in this paper has implications for retailers and policymakers as it points to concrete action points to enhance dietary imbalances and underconsumption of low-income and cognitively constrained individuals. I discuss a specific use case of the algorithm for people with intellectual and developmental disabilities.
Preferences for Cash vs. Card Payments: An Analysis using German Household Scanner Data
This Version: May 2020
Abstract: This paper studies preferences for cash versus card payments using household scanner data of up to 18,000 German households from 2009 to 2015. I exploit a unique institutional setting in which virtually all households have access free-of-charges to the same debit card, the girocard, which has the same liquidity as cash, and which allows to make payments of any denomination at all considered retailers without any additional benefits or costs. Accounting for household fixed effects and thus also unexplained household preferences, the paper shows that cash usage hardly decreases in the aggregate over these seven years. The estimated decline in cash usage over time becomes substantially smaller compared to a model without fixed effects and thus as suggested by earlier studies. Still, I find that, individually, households exhibit great differences in their use of cash vs. card payments but that these differences are also individually persistent over the course of the covered seven years. The particular institutional environment and the long-term panel structure of the data allow me to rule out other common explanations for households’ payment choices.
Policy Publications
Job Creation and Demand for Skills in Kosovo: What Can We Learn from Job Portal Data?
with Alicia Marguerie and Stefanie Brodmann
World Bank Policy Research Working Paper 9266
This Version: June 2020
Abstract: In Kosovo, employers report significant skill shortages, which limits firm growth and job creation. To understand the labor market dynamics and employer needs in real time, this paper analyzes the content of job postings using data from major online job portals from 2018. The findings show that the skills that are most in demand are socioemotional skills (especially related to extraversion), foreign language skills, and computer skills. The importance of these skills is transversal, cutting not only across occupations and industries, but also universally demanded in all education fields. The need for these skills is expressed more often and more explicitly in postings for jobs requiring higher levels of experience. Moreover, job platforms are used almost exclusively for filling high-skill occupations, especially in Kosovo's capital city, Pristina, whereas many low- and medium-skill jobs and jobs outside the capital are filled through informal channels. Overall, online data can be a useful tool for policy makers and other stakeholders to help align career services, training programs, and educational curricula with the skill needs of firms in real time.
Other Policy Work
Monitoring Real-Time Labor Market Trends Through Online Job Vacancies
Conducted data collection and analyis for policy briefs written by Alicia Marguerie, Stefanie Brodmann and Cornelius von Lenthe
This Version: May 2021
Abstract: In dynamic economies, real-time labor market information based on online sources has become an integral part of labor market monitoring and is increasingly used to inform policy decisions. Data from online job portals complements rather than replace existing sources of labor market information and can be used to inform career guidance for young and unemployed people as well as programing decisions in education and training, as input into curricula or for business support services. With the onset of the Coronavirus disease 2019 (COVID-19) crisis, the availability of readily available labor market information has become even more relevant. The World Bank has started collecting information on vacancies from online job portals in Kosovo since 2019 and three other Western Balkan countries since May 2020.
Download policy brief for Kosovo | Download policy brief for Albania
Disclaimer: This is my private web page and the views expressed in the material posted here are my own and do not reflect those of the European Central Bank or of the Eurosystem.