David
Bounie
Professor at Télécom Paris, Institut Polytechnique de Paris
Visiting Professor, McGill University — 2026–2027
High-Frequency Data · Digital Markets · Computational Statistics
Professor at Télécom Paris, Institut Polytechnique de Paris
Visiting Professor, McGill University — 2026–2027
High-Frequency Data · Digital Markets · Computational Statistics
"Leveraging granular, high-frequency data to understand how money moves, consumers behave, markets respond, and regulation adapts."
I am a Full Professor at Télécom Paris, Institut Polytechnique de Paris, and a Visiting Professor at McGill University for the 2026–2027 academic year. I am based at the Center for Research in Economics and Statistics (CREST) and an Academic Fellow at the Institut Louis Bachelier.
My work uses large, granular datasets — card transactions, mobile phone data — to answer concrete questions about how people spend, move, and are affected by policy and events. Recent work has looked at how consumers shift their spending across regions and online versus offline, and how local businesses are affected by things like new cycling infrastructure, telework, consumption externalities, extreme weather events, and sports competitions.
I also study digital markets: who profits when consumer data is bought and sold and what that means for competition between firms, as well as how payment technology is reshaping how people pay — from the effect of debit cards on cash use to contactless payment and, looking ahead, central bank digital currencies and stablecoins.
Much of this work relies on methods I develop myself, including fast algorithms for analyzing very large datasets — one runs up to 7,000 times faster than existing approaches — with applications such as fraud detection.
I co-direct the Digital Finance Research Chair at Télécom Paris, in partnership with the Groupement des Cartes Bancaires CB, Caisse des Dépôts, INSEE, and Institut Louis Bachelier.
My recent work follows four main lines of research.
The first is empirical and relies on causal inference methods, using granular, high-frequency data — card transactions, mobile phone data — to revisit inter-regional trade (International Economic Review, 2026) and aggregate consumption dynamics (European Economic Review, 2023). This line extends to the local economic effects of specific events and policies, including cycling infrastructure (R&R, Journal of Economic Geography), telework, consumption externalities, extreme weather events, and sports competitions.
The second is grounded in industrial organization, and concerns data intermediaries in the digital economy — how data brokers collect and sell consumer information to firms, and how this affects competition in digital markets — with publications in The RAND Journal of Economics (2021) and the International Journal of Industrial Organization (2025), as well as ongoing work on competition and mergers among data intermediaries (R&R, International Journal of Industrial Organization).
The third is computational and statistical, developing scalable methods for high-dimensional data analysis, including a GPU-based algorithm for projection-based statistical depths (R&R, Computational Statistics & Data Analysis), with applications to fraud detection.
The fourth concerns the economics of payments and digital finance, including the effect of debit cards on demand for cash (Journal of Banking & Finance, 2016) and of contactless technology on merchant card sales (Journal of Banking & Finance, 2020), with ongoing work on CBDCs and stablecoins.
This article uses geo-located card transactions to build consumer mobility and inter-regional trade measures, allowing comparison of online and offline inter-regional purchases on a common sample of merchants which each conduct both offline and online card transactions.
This article analyzes how take-it-or-leave-it offers (TIOLI) and auctions impact the selling strategy of a data intermediary, the price of information and the amount of consumer data collected.
This article analyzes the relationship between privacy protection and market competition. Firms strategically choose the number of consumers on whom they collect data — the extensive margin of privacy — as well as the precision of information — the intensive margin of privacy.
This paper investigates the effects of the pandemic containment periods in France on individuals' movements, expenditure and adaptation to the shock, using billions of French bank card transactions measured before and during the COVID-19 pandemic.
This paper investigates the strategies of a data broker in selling information to one or to two competing firms that can price-discriminate consumers.
Using anonymised French transaction and bank data, this paper tracks consumption and savings dynamics from the onset of the pandemic: a severe drop during lockdown, a strong summer rebound, and a sharp rise in aggregate household savings that was highly concentrated at the top of the income distribution.
Using score-matching and difference-in-differences on roughly 275,000 French merchants, this paper shows that accepting contactless card payments in 2018 raised card-sales value by 15.3% on average, with a positive spillover of 1.3% on contact card sales at the same merchants.
This paper studies how competing data intermediaries collect and sell consumer information to firms for price discrimination. It shows that competition among intermediaries benefits consumers, both by intensifying downstream competition and by curbing the volume of data collected, with implications for how merger policy should treat large data intermediaries.
This paper introduces a new algorithmic framework, Refined Random Search, for computing projection-based statistical depths at scale in high-dimensional settings. Run on GPUs, the method delivers up to a 7,000-fold speedup over existing approaches while improving precision, and is released as an open-source Python library.
Using geo-located card transaction data, this paper evaluates the local economic impact of Paris's large-scale cycling infrastructure investment, the Plan Vélo. Areas that gained better access to the new network saw brick-and-mortar spending rise by 4.4% per quarter, with the largest gains for smaller and younger businesses, alongside a measurable drop in car traffic.
Combining high-frequency mobile phone and card transaction data from the Lyon metropolitan area, this paper identifies two opposing demand shocks: a 1-point increase in working from home raises local spending by 1%, while a 1-point rise in workplace absence reduces it by 1.3%, clarifying whether telework redistributes or genuinely reduces local demand.
This paper combines high-frequency mobile phone location data with card transaction records to study how the number of people present in a zone at a given moment ("real-time population") relates to local spending, estimating this elasticity across more than a thousand zones in the Lyon metropolitan area.
Using high-frequency card transaction and reimbursement data spanning 2018–2023, this paper estimates weekly and annual return rates for online and in-store purchases, isolating the effects of e-commerce growth and the COVID-19 shock, and finds lasting changes in online return behavior for durable goods with potential environmental costs.
Address19 Place Marguerite Perey
Office 3A483, 91120 Palaiseau, France
Emaildavid.bounie@telecom-paris.fr
Phone+33 1 75 31 98 80
