The DOI matches its Crossref record; 54 of the 54 references it cites were found in a registry or an index.
Customer Acquisition via Display Advertising Using Multi-Armed Bandit Experiments
Abstract
Firms using online advertising regularly run experiments with multiple versions of their ads since they are uncertain about which ones are most effective. During a campaign, firms try to adapt to intermediate results of their tests, optimizing what they earn while learning about their ads. Yet how should they decide what percentage of impressions to allocate to each ad? This paper answers that question, resolving the well-known “learn-and-earn” trade-off using multi-armed bandit (MAB) methods. The online advertiser’s MAB problem, however, contains particular challenges, such as a hierarchical structure (ads within a website), attributes of actions (creative elements of an ad), and batched decisions (millions of impressions at a time), that are not fully accommodated by existing MAB methods. Our approach captures how the impact of observable ad attributes on ad effectiveness differs by website in unobserved ways, and our policy generates allocations of impressions that can be used in practice. We implemented this policy in a live field experiment delivering over 750 million ad impressions in an online display campaign with a large retail bank. Over the course of two months, our policy achieved an 8% improvement in the customer acquisition rate, relative to a control policy, without any additional costs to the bank. Beyond the actual experiment, we performed counterfactual simulations to evaluate a range of alternative model specifications and allocation rules in MAB policies. Finally, we show that customer acquisition would decrease by about 10% if the firm were to optimize click-through rates instead of conversion directly, a finding that has implications for understanding the marketing funnel. Data is available at https://doi.org/10.1287/mksc.2016.1023 .
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Gelman, A., Carlin, J. B., Stern, H. S., & Rubin, D. B. (2003) · doi:10.1201/9780429258480 · Cited by 27,276
Reinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. G. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.1998.712192 · Cited by 27,225
Data Analysis Using Regression and Multilevel/Hierarchical Models
Gelman, A., & Hill, J. (2006) · doi:10.1017/cbo9780511790942 · Cited by 13,597
Estimating causal effects of treatments in randomized and nonrandomized studies
Rubin, D. B. (1974) · Journal of Educational Psychology · doi:10.1037/h0037350 · Cited by 9,436
Finite-time Analysis of the Multiarmed Bandit Problem
Auer, P., Cesa-Bianchi, N., & Fischer, P. (2002) · Machine Learning · doi:10.1023/a:1013689704352 · Cited by 6,033
Nonlinear Regression Analysis and Its Applications
Bates, D. M., & Watts, D. G. (1988) · Wiley Series in Probability and Statistics · doi:10.1002/9780470316757 · Cited by 3,979
THOMPSON, W. R. (1933) · Biometrika · doi:10.1093/biomet/25.3-4.285 · Cited by 2,712
Approximate Dynamic Programming: Solving the Curses of Dimensionality
Powell, W. B. (2011) · Wiley Series in Probability and Statistics · doi:10.1002/9781118029176 · Cited by 2,297
Some aspects of the sequential design of experiments
Robbins, H. (1952) · Bulletin of the American Mathematical Society · doi:10.1090/s0002-9904-1952-09620-8 · Cited by 2,184
Bandit processes and dynamic allocation indices
Gittins, J. C. (1979) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1979.tb01068.x · Cited by 1,487
Reinforcement Learning: An Introduction
(1998) · Kybernetes · doi:10.1108/k.1998.27.9.1093.3 · Cited by 1,472
Using confidence bounds for exploitation-exploration trade-offs
Auer, P. L. (2003) · Journal of Machine Learning Research · doi:10.5555/944919.944941 · Cited by 1,229
(2011) · Cited by 1,000
Multi-Armed Bandit Allocation Indices.
Bather, J. A., & Gittins, J. C. (1990) · Journal of the Royal Statistical Society. Series A (Statistics in Society) · doi:10.2307/2982809 · Cited by 998
Analysis of Thompson Sampling for the multi-armed bandit problem
Agrawal, S., & Goyal, N. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1111.1797 · Cited by 819
Online Display Advertising: Targeting and Obtrusiveness
Goldfarb, A., & Tucker, C. (2011) · Marketing Science · doi:10.1287/mksc.1100.0583 · Cited by 815
An experimental design for the development of adaptive treatment strategies
Murphy, S. A. (2005) · Statistics in Medicine · doi:10.1002/sim.2022 · Cited by 746
Multi‐Armed Bandit Allocation Indices
Gittins, J., Glazebrook, K., & Weber, R. (2011) · Wiley eBooks · doi:10.1002/9780470980033 · Cited by 684
Berry, D. A., & Fristedt, B. (1985) · Springer eBooks · doi:10.1007/978-94-015-3711-7 · Cited by 633
(2008) · ScholarlyCommons (University of Pennsylvania) · Cited by 581
Sample mean based index policies by O(log n) regret for the multi-armed bandit problem
Agrawal, R. (1995) · Advances in Applied Probability · doi:10.2307/1427934 · Cited by 540
Multi-Armed Bandits and the Gittins Index
Whittle, P. (1980) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1980.tb01111.x · Cited by 514
When Does Retargeting Work? Information Specificity in Online Advertising
Lambrecht, A., & Tucker, C. (2013) · Journal of Marketing Research · doi:10.1509/jmr.11.0503 · Cited by 508
Learning to Optimize via Posterior Sampling
Russo, D., & Van Roy, B. (2014) · Mathematics of Operations Research · doi:10.1287/moor.2014.0650 · Cited by 493
The Effect of Banner Advertising on Internet Purchasing
Manchanda, P., Dubé, J.-P., Goh, K. Y., & Chintagunta, P. K. (2006) · Journal of Marketing Research · doi:10.1509/jmkr.43.1.98 · Cited by 456
Linearly Parameterized Bandits
Rusmevichientong, P., & Tsitsiklis, J. N. (2010) · Mathematics of Operations Research · doi:10.1287/moor.1100.0446 · Cited by 427
The Knowledge-Gradient Policy for Correlated Normal Beliefs
Frazier, P., Powell, W., & Dayanik, S. (2009) · INFORMS Journal on Computing · doi:10.1287/ijoc.1080.0314 · Cited by 408
A modern Bayesian look at the multi‐armed bandit
Scott, S. L. (2010) · Applied Stochastic Models in Business and Industry · doi:10.1002/asmb.874 · Cited by 406
Thompson Sampling: An Asymptotically Optimal Finite-Time Analysis
Kaufmann, E., Korda, N., & Munos, R. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-34106-9_18 · Cited by 365
Hauser, J. R., Urban, G. L., Liberali, G., & Braun, M. (2009) · Marketing Science · doi:10.1287/mksc.1080.0459 · Cited by 292
Adaptive Treatment Allocation and the Multi-Armed Bandit Problem
Lai, T. L. (1987) · The Annals of Statistics · doi:10.1214/aos/1176350495 · Cited by 279
Parametric Bandits: The Generalized Linear Case
Filippi, S., Cappé, O., Garivier, A., & Szepesvári, C. (2010) · Cited by 259
Optimistic bayesian sampling in contextual-bandit problems
May, B. C., Korda, N., Lee, A., & Leslie, D. S. (2012) · Lancaster EPrints (Lancaster University) · doi:10.82444/warw.33678499 · Cited by 213
Hoban, P. R., & Bucklin, R. E. (2015) · Journal of Marketing Research · doi:10.1509/jmr.13.0277 · Cited by 191
Bayesian Statistics and the Efficiency and Ethics of Clinical Trials
Berry, D. A. (2004) · Statistical Science · doi:10.1214/088342304000000044 · Cited by 183
Perchet, V., Rigollet, P., Chassang, S., & Snowberg, E. (2016) · The Annals of Statistics · doi:10.1214/15-aos1381 · Cited by 151
Sequential Sampling to Myopically Maximize the Expected Value of Information
Chick, S. E., Branke, J., & Schmidt, C. (2009) · INFORMS journal on computing · doi:10.1287/ijoc.1090.0327 · Cited by 151
Solving two‐armed Bernoulli bandit problems using a Bayesian learning automaton
Granmo, O. (2010) · International Journal of Intelligent Computing and Cybernetics · doi:10.1108/17563781011049179 · Cited by 145
A Minimum Relative Entropy Principle for Learning and Acting
Ortega, P. A., & Braun, D. A. (2010) · Journal of Artificial Intelligence Research · doi:10.1613/jair.3062 · Cited by 135
Online Advertising Response Models: Incorporating Multiple Creatives and Impression Histories
Braun, M. I., & Moe, W. W. (2011) · Marketing Science · doi:10.1287/mksc.2013.0802 · Cited by 130
Explore/Exploit Schemes for Web Content Optimization
Agarwal, D., Chen, B.-C., & Elango, P. (2009) · Proceedings · doi:10.1109/icdm.2009.52 · Cited by 123
Berry, D. A. (1972) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177692553 · Cited by 119
Sequential Choice Under Ambiguity: Intuitive Solutions to the Armed-Bandit Problem
Meyer, R. J., & Shi, Y. (1995) · Management Science · doi:10.1287/mnsc.41.5.817 · Cited by 113
Optimal learning and experimentation in bandit problems
Brezzi, M., & Lai, T. L. (2002) · Journal of Economic Dynamics and Control · doi:10.1016/s0165-1889(01)00028-8 · Cited by 109
How to design smart business experiments
Davenport, T. H. (2009) · Strategic Direction · doi:10.1108/sd.2009.05625had.004 · Cited by 101
Urban, G. L., Liberali, G., MacDonald, E. F., Bordley, R. F., & Hauser, J. R. (2013) · Marketing Science · doi:10.1287/mksc.2013.0803 · Cited by 100
A Learning Approach for Interactive Marketing to a Customer Segment
Bertsimas, D., & Mersereau, A. J. (2007) · Operations Research · doi:10.1287/opre.1070.0427 · Cited by 99
Sequential Sampling with Economics of Selection Procedures
Chick, S. E., & Frazier, P. I. (2011) · Management Science · doi:10.1287/mnsc.1110.1425 · Cited by 89
Bandit Algorithms for Website Optimization
White, J. M. (2012) · CERN Document Server (European Organization for Nuclear Research) · Cited by 83
Website Morphing 2.0: Switching Costs, Partial Exposure, Random Exit, and When to Morph
Hauser, J. R., Liberali, G., & Urban, G. L. (2014) · Management Science · doi:10.1287/mnsc.2014.1961 · Cited by 55
Learning from Experience, Simply
Lin, S., Zhang, J., & Hauser, J. R. (2012) · Marketing Science · doi:10.1287/mksc.2014.0868 · Cited by 48
Display advertising impact: search lift and social influence
Papadimitriou, P., García-Molina, H., Krishnamurthy, P., Lewis, R. A., & Reiley, D. (2011) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2020408.2020572 · Cited by 20
Bayesian Rules for the Two-Armed Bandit Problem
Wahrenberger, D. L., Antle, C. E., & Klimko, L. A. (1977) · Biometrika · doi:10.1093/biomet/64.1.172 · Cited by 17
Branching bandits: a sequential search process with correlated pay-offs
Keller, G., & Oldale, A. (2003) · Journal of Economic Theory · doi:10.1016/s0022-0531(03)00092-9 · Cited by 14
Cited by
Machine learning and AI in marketing–Connecting computing power to human insights
Ma, L., & Sun, B. (2020) · International Journal of Research in Marketing · doi:10.1016/j.ijresmar.2020.04.005 · Cited by 602
Artificial Intelligence and Marketing: Pitfalls and Opportunities
De Bruyn, A., Viswanathan, V., Beh, Y. S., Brock, J. K.-U., & Von Wangenheim, F. (2020) · Journal of Interactive Marketing · doi:10.1016/j.intmar.2020.04.007 · Cited by 515
A Tutorial on Thompson Sampling
Russo, D. J., Van Roy, B., Kazerouni, A., Osband, I., & Wen, Z. (2018) · now publishers, Inc. eBooks · doi:10.1561/9781680834710 · Cited by 380
Brave New World? On AI and the Management of Customer Relationships
Libai, B., Bart, Y., Gensler, S., Hofacker, C. F., Kaplan, A., Kötterheinrich, K., & Kroll, E. B. (2020) · Journal of Interactive Marketing · doi:10.1016/j.intmar.2020.04.002 · Cited by 358
The power of generative marketing: Can generative AI create superhuman visual marketing content?
Hartmann, J., Exner, Y., & Domdey, S. (2025) · International Journal of Research in Marketing · doi:10.1016/j.ijresmar.2024.09.002 · Cited by 229
Metadata
- Authors
- Schwartz, E. M., Bradlow, E. T., & Fader, P. S.
- Venue
- Marketing Science
- Published
- 2017-07
- Volume
- 36
- Issue
- 4
- Pages
- 500-522
- ISSN
- 0732-2399 (ISSN-L)
- 1526-548X
- OpenAlex
- W3121632328
- Cited by
- 260
- References
- 54
- FWCI
- 20.07
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.