Multi-objective evolutionary product bundling

A case study

Conference paper (2021)

Authors

Okan Tunali Ata Technology Platforms, İstanbul
Ahmet Turul Bayrak Ata Technology Platforms, İstanbul
V Sanchez-Anguix Universitat Politécnica de Valencia
Reyhan Aydoğan Interactive Intelligence - EEMCS , Özyeğin University
Research Group
Interactive Intelligence (EEMCS) (TU Delft)
Genetic algorithm Multi-objective optimization Decision support systems Evolutionary algorithms Bundle generation
More Info
expand_more

Published Date

2021

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Department

Intelligent Systems

Research Group

Interactive Intelligence

Abstract

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.

Files

3449726.3463219.pdf
(.pdf | 0.988 Mb)