Multi-objective evolutionary product bundling
Autor: | Victor Sanchez-Anguix, Okan Tunali, Reyhan Aydoğan, Ahmet Tugrul Bayrak |
---|---|
Rok vydání: | 2021 |
Předmět: |
education.field_of_study
Mathematical optimization Computer science business.industry Population Evolutionary algorithm Pareto principle Decision support systems Evolutionary algorithms Multi-objective optimization Genetic algorithm User experience design Bundle Bundle generation CIENCIAS DE LA COMPUTACION E INTELIGENCIA ARTIFICIAL Product (category theory) business education |
Zdroj: | GECCO Companion |
Popis: | [EN] Product bundling is a strategy conducted by marketing decisionmakers 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 showthat the evolutionary approach enables us to generate Pareto solutions compared to the initial population. |
Databáze: | OpenAIRE |
Externí odkaz: |