Multi-objective evolutionary product bundling: a case study

Product bundling is a strategy conducted by marketing decision-makers to combine items or services for targeted sales in today's competitive business environment. Targeted sales can be in various forms, like increasing the likelihood of a purchase, promoting some products among a specific customer segment, or improving user experience. In this study, we propose an evolutionary product bundle generation strategy that is based on the NSGA-II algorithm. The proposed approach is designed as a multi-objective optimization procedure where the objectives are designed in terms of desired bundle feature distributions. The designed genetic algorithm is flexible and allows decision-makers to specify objectives such as price, season, item similarity and association with bundle size constraints. In the experiments, we show that the evolutionary approach enables us to generate Pareto solutions compared to the initial population.

[1]  Lior Rokach,et al.  Introduction to Recommender Systems Handbook , 2011, Recommender Systems Handbook.

[2]  Chang Zhou,et al.  Personalized Bundle List Recommendation , 2019, WWW.

[3]  Wenqiang Zhang,et al.  Recent advances in hybrid evolutionary algorithms for multiobjective manufacturing scheduling , 2017, Comput. Ind. Eng..

[4]  Gary J. Russell,et al.  Emerging Trends in Product Bundling: Investigating Consumer Choice and Firm Behavior , 2018 .

[5]  Tea Tusar,et al.  Visualizing 4D approximation sets of multiobjective optimizers with prosections , 2011, GECCO '11.

[6]  Afonso C. C. Lemonge,et al.  A rank-based constraint handling technique for engineering design optimization problems solved by genetic algorithms , 2017 .

[7]  Elli Rapti,et al.  Dynamic Generation of Personalized Product Bundles in Enterprise Networks , 2013, OTM Workshops.

[8]  Vicente Julián,et al.  A near Pareto optimal approach to student-supervisor allocation with two sided preferences and workload balance , 2018, Appl. Soft Comput..

[9]  R. Agarwal.  Fast Algorithms for Mining Association Rules , 1994, VLDB 1994.

[10]  Mohammad Reza Gholamian,et al.  A novel model for product bundling and direct marketing in e-commerce based on market segmentation , 2018 .

[11]  Lior Rokach,et al.  Recommender Systems for Product Bundling , 2016, RecSys Posters.

[12]  Julian J. McAuley,et al.  Generating and Personalizing Bundle Recommendations on Steam , 2017, SIGIR.

[13]  Tzyy-Ching Yang,et al.  Comparison of product bundling strategies on different online shopping behaviors , 2006, Electron. Commer. Res. Appl..

[14]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[15]  Yong-Wu Zhou,et al.  Pricing and Product-bundling Strategies for E-commerce Platforms with Competition , 2020, Eur. J. Oper. Res..

[16]  M. Sheikhzadeh,et al.  Product bundling: Impacts of product heterogeneity and risk considerations , 2013 .

[17]  Li-Hua Li,et al.  The personalized recommendation with bundling strategy based on product consuming period , 2009 .

[18]  Pierluigi Ritrovato,et al.  Searching optimal product bundles by means of GA-based Engine and Market Basket Analysis , 2013, 2013 Joint IFSA World Congress and NAFIPS Annual Meeting (IFSA/NAFIPS).

[19]  Hagai Attias,et al.  A Variational Bayesian Framework for Graphical Models , 1999 .

[20]  Manoj K. Agarwal,et al.  Complexity, uniqueness, and similarity in between‐bundle choice , 2003 .