skip to main content
10.1145/3298689.3347027acmotherconferencesArticle/Chapter ViewAbstractPublication PagesrecsysConference Proceedingsconference-collections
research-article

LORE: a large-scale offer recommendation engine with eligibility and capacity constraints

Published: 10 September 2019 Publication History

Abstract

Businesses, such as Amazon, department store chains, home furnishing store chains, Uber, and Lyft, frequently offer deals, product discounts and incentives to drive sales, increase new product acceptance and engage with users. In order to appeal to diverse user groups, these businesses typically design more than one promotion offer but market different ones to different users. For instance, Uber offers a percentage discount in the rides to some users and a low fixed price to others. In this paper, we propose solutions to optimally recommend promotions and items to maximize user conversion constrained by user eligibility and item or offer capacity (limited quantity of items or offers) simultaneously. We achieve this through an offer recommendation model based on Min-Cost Flow network optimization, which enables us to satisfy the constraints within the optimization itself and solve it in polynomial time. We present two approaches that can be used in various settings: single period solution and sequential time period offering. We evaluate these approaches against competing methods using counterfactual evaluation in offline mode. We also discuss three practical aspects that may affect the online performance of constrained optimization: capacity determination, traffic arrival pattern and clustering for large scale setting.

References

[1]
Parameswaran Aditya, Venetis Petros, and Hector Garcia-Molina. 2011. Recommendation Systems with Complex Constraints: A Course Recommendation Perspective. ACM Trans. Inf. Syst. 29, 4, Article 20 (Dec. 2011), 33 pages.
[2]
Deepak Agarwal, Shaunak Chatterjee, Yang Yang, and Liang Zhang. 2015. Constrained optimization for homepage relevance. (2015), 375--384.
[3]
Shipra Agrawal and Nikhil R. Devanur. 2015. Fast Algorithms for Online Stochastic Convex Programming. (2015), 1405--1424.
[4]
Shipra Agrawal, Zizhuo Wang, and Yinyu Ye. 2014. A Dynamic Near-Optimal Algorithm for Online Linear Programming. Oper. Res. 62, 4 (Aug. 2014), 876--890.
[5]
Ashwinkumar Badanidiyuru, Robert Kleinberg, and Aleksandrs Slivkins. 2018. Bandits with Knapsacks. J. ACM 65, 3, Article 13 (March 2018), 55 pages.
[6]
Joseph Konstan Badrul Sarwar, George Karypis and John Riedl. 2001. Item-based collaborative filtering recommendation algorithms. Proceedings of the 10th international conference on World Wide Web (2001), 285--295.
[7]
D.P. Bertsekas. 1991. Linear Network Optimization. MIT Press, Cambridge, MA (1991).
[8]
Andy Liaw Chao Chen and Leo Breiman. 2004. Using Random Forest to Learn Imbalanced Data. https://statistics.berkeley.edu/tech-reports/666 (2004).
[9]
Young Choi Deuk H. Park, Hyea K. Kim and Jae K. Kim. 2012. A literature review and classification of recommender systems research. Expert Systems with Applications (2012), 10059--10072.
[10]
Miroslav Dudík, John Langford, and Lihong Li. 2011. Doubly Robust Policy Evaluation and Learning. (2011), 1097--1104. http://dl.acm.org/citation.cfm?id=3104482.3104620
[11]
Guillermo Gallego and Garrett van Ryzin. 1994. Optimal Dynamic Pricing of Inventories with Stochastic Demand over Finite Horizons. Manage. Sci. 40, 8 (Aug. 1994), 999--1020.
[12]
Negin Golrezaei, Hamid Nazerzadeh, and Paat Rusmevichientong. 2014. Real-Time Optimization of Personalized Assortments. Manage. Sci. 60, 6 (June 2014), 1532--1551.
[13]
Trevor Hastie, Robert Tibshirani, and Jerome Friedman. 2001. The Elements of Statistical Learning. (2001).
[14]
T. Hesterberg. 1995. Weighted average importance sampling and defensive mixture distributions. Technometrics, pp. 185--194, (1995).
[15]
Kevin Hillstrom. 2008. The MineThatData e-mail analytics and data mining challenge. http://blog.minethatdata.com/2008/03/minethatdata-e-mailanalytics-and-data.html (2008).
[16]
Edward L. Ionides. 2008. Truncated importance sampling. Journal of Computational and Graphical Statistics, 17(2):295-311 (2008).
[17]
László A Jeni, Jeffrey F Cohn, and Fernando De La Torre. 2013. Facing Imbalanced Data-Recommendations for the Use of Performance Metrics. (2013), 245--251.
[18]
Thorsten Joachims and Adith Swaminathan. 2016. Counterfactual Evaluation and Learning for Search, Recommendation and Ad Placement. (2016), 1199--1201.
[19]
Pooria Joulani, Andras Gyorgy, and Csaba Szepesvári. 2013. Online learning under delayed feedback. (2013), 1453--1461.
[20]
Jaya Kawale Konstantina Christakopoulou and Arindam Banerjee. 2017. Recommendation with Capacity Constraints. ACM on Conference on Information and Knowledge Management (2017), 1439--1448.
[21]
Diane Lambert and Daryl Pregibon. 2007. More Bang for Their Bucks: Assessing New Features for Online Advertisers. (2007), 7--15.
[22]
Tor Lattimore and Csaba Szepesvari. 2018. Bandit Algorithms. (2018).
[23]
Damien Lefortier, Adith Swaminathan, Xiaotao Gu, Thorsten Joachims, and Maarten de Rijke. 2016. Large-scale Validation of Counterfactual Learning Methods: A Test-Bed. CoRR abs/1612.00367 (2016). arXiv:1612.00367 http://arxiv.org/abs/1612.00367
[24]
Lihong Li, Shunbao Chen, Jim Kleban, and Ankur Gupta. 2015. Counterfactual Estimation and Optimization of Click Metrics in Search Engines: A Case Study. (2015), 929--934.
[25]
Dudík Miroslav; Erhan Dumitru; Langford John; Li Lihong. 2014. Doubly Robust Policy Evaluation and Optimization. Statistical Science, Vol. 29, No. 4, 485--511; (2014).
[26]
D. Lo, V.S.Y.; Pachamanova. 2015. From Predictive Uplift Modeling to Prescriptive Uplift Analytics: A Practical Approach to Treatment Optimization While Accounting for Estimation Risk. Journal of Marketing Analytics, 3 (2): 95 (2015).
[27]
Victor S. Y. Lo. 2002. The True Lift Model: A Novel Data Mining Approach to Response Modeling in Database Marketing. SIGKDD Explor. Newsl. 4, 2 (Dec. 2002), 78--86.
[28]
Harry Markowitz. 1952. Portfolio Selection. The Journal of Finance, vol. 7, no. 1, pp. 77--91 (1952).
[29]
Aranyak Mehta, Amin Saberi, Umesh Vazirani, and Vijay Vazirani. 2007. Adwords and generalized online matching. Journal of the ACM (JACM) 54, 5 (2007), 22.
[30]
Alexandru Niculescu-Mizil and Rich Caruana. 2005. Predicting Good Probabilities with Supervised Learning. (2005), 625--632.
[31]
N. J.; Radcliffe and P. D. Surry. 1999. Differential response analysis: Modelling true response by isolating the effect of a single action, in Proceedings of Credit Scoring and Credit Control VI, Credit Research Centre, University of Edinburgh Management School (1999).
[32]
P. Rosenbaum and D. Rubin. 1983. The central role of the propensity score in observational studies for causal effects. Biometrika, 70(1):41-55, (1983).
[33]
Aixin Sun Shuai Zhang, Lina Yao and Yi Tay. 2018. Deep Learning based Recommender System: A Survey and New Perspectives. ACM computer survey 1 (2018), Article 1, 35 pages.
[34]
L. Si and R. Jin. 2003. Flexible mixture model for collaborative filtering. Proceedings of the 20th International Conference on Machine Learning (ICML '03) (2003), 704--711.
[35]
Cohen Maxime C; Ngai-Hang Z Leung; Kiran Panchamgam; Georgia Perakis; Anthony Smith. 2017. The impact of linear optimization on promotion planning. Operations Research 65(2) (2017), 446--448.
[36]
Xiaoyuan Su and Taghi Khoshgoftaar. 2009. A survey of collaborative filtering techniques. Advances in Artificial Intelligence (2009), Article ID 421425, 19 pages.
[37]
Adith Swaminathan and Thorsten Joachims. 2015. The Self-normalized Estimator for Counterfactual Learning. (2015), 3231--3239. http://dl.acm.org/citation.cfm?id=2969442.2969600

Cited By

View all
  • (2024)End-to-End Cost-Effective Incentive Recommendation under Budget Constraint with Uplift ModelingProceedings of the 18th ACM Conference on Recommender Systems10.1145/3640457.3688147(560-569)Online publication date: 8-Oct-2024
  • (2023)Uplift Modeling: From Causal Inference to PersonalizationProceedings of the 32nd ACM International Conference on Information and Knowledge Management10.1145/3583780.3615298(5212-5215)Online publication date: 21-Oct-2023
  • (2023)Much Ado About GenderProceedings of the 2023 Conference on Human Information Interaction and Retrieval10.1145/3576840.3578316(269-279)Online publication date: 19-Mar-2023
  • Show More Cited By

Index Terms

  1. LORE: a large-scale offer recommendation engine with eligibility and capacity constraints

        Recommendations

        Comments

        Information & Contributors

        Information

        Published In

        cover image ACM Other conferences
        RecSys '19: Proceedings of the 13th ACM Conference on Recommender Systems
        September 2019
        635 pages
        ISBN:9781450362436
        DOI:10.1145/3298689
        Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

        Publisher

        Association for Computing Machinery

        New York, NY, United States

        Publication History

        Published: 10 September 2019

        Permissions

        Request permissions for this article.

        Check for updates

        Author Tags

        1. budget constraint
        2. min-cost flow
        3. recommendation systems

        Qualifiers

        • Research-article

        Conference

        RecSys '19
        RecSys '19: Thirteenth ACM Conference on Recommender Systems
        September 16 - 20, 2019
        Copenhagen, Denmark

        Acceptance Rates

        RecSys '19 Paper Acceptance Rate 36 of 189 submissions, 19%;
        Overall Acceptance Rate 254 of 1,295 submissions, 20%

        Contributors

        Other Metrics

        Bibliometrics & Citations

        Bibliometrics

        Article Metrics

        • Downloads (Last 12 months)24
        • Downloads (Last 6 weeks)1
        Reflects downloads up to 17 Jan 2025

        Other Metrics

        Citations

        Cited By

        View all
        • (2024)End-to-End Cost-Effective Incentive Recommendation under Budget Constraint with Uplift ModelingProceedings of the 18th ACM Conference on Recommender Systems10.1145/3640457.3688147(560-569)Online publication date: 8-Oct-2024
        • (2023)Uplift Modeling: From Causal Inference to PersonalizationProceedings of the 32nd ACM International Conference on Information and Knowledge Management10.1145/3583780.3615298(5212-5215)Online publication date: 21-Oct-2023
        • (2023)Much Ado About GenderProceedings of the 2023 Conference on Human Information Interaction and Retrieval10.1145/3576840.3578316(269-279)Online publication date: 19-Mar-2023
        • (2023)Sustainability-oriented Recommender SystemsProceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization10.1145/3565472.3595617(296-300)Online publication date: 18-Jun-2023
        • (2022)E-Commerce Promotions Personalization via Online Multiple-Choice Knapsack with Uplift ModelingProceedings of the 31st ACM International Conference on Information & Knowledge Management10.1145/3511808.3557100(2863-2872)Online publication date: 17-Oct-2022
        • (2022)LBCF: A Large-Scale Budget-Constrained Causal Forest AlgorithmProceedings of the ACM Web Conference 202210.1145/3485447.3512103(2310-2319)Online publication date: 25-Apr-2022
        • (2021)Multi-Objective Recommendations and Promotions at TOTALDatabase and Expert Systems Applications10.1007/978-3-030-86475-0_27(270-282)Online publication date: 1-Sep-2021
        • (2021)Equality of Opportunity in Ranking: A Fair-Distributive ModelAdvances in Bias and Fairness in Information Retrieval10.1007/978-3-030-78818-6_6(51-63)Online publication date: 25-Jun-2021
        • (2020)Free Lunch! Retrospective Uplift Modeling for Dynamic Promotions Recommendation within ROI ConstraintsProceedings of the 14th ACM Conference on Recommender Systems10.1145/3383313.3412215(486-491)Online publication date: 22-Sep-2020

        View Options

        Login options

        View options

        PDF

        View or Download as a PDF file.

        PDF

        eReader

        View online with eReader.

        eReader

        Media

        Figures

        Other

        Tables

        Share

        Share

        Share this Publication link

        Share on social media