Clonal selection algorithms for optimal product line design: A comparative study

• Published in: European journal of operational research Vol. 298; no. 2; pp. 585 - 595
• Main Authors: Pantourakis, Michail, Tsafarakis, Stelios, Zervoudakis, Konstantinos, Altsitsiadis, Efthymios, Andronikidis, Andreas, Ntamadaki, Vasiliki
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 16.04.2022
• Subjects: Clonal selection algorithm; Combinatorial optimization; Or in marketing; Product line design; Product line design; Or in marketing; Combinatorial optimization; Clonal selection algorithm
• ISSN: 0377-2217; 1872-6860
• DOI: 10.1016/j.ejor.2021.07.006

•23 Clonal selection algorithm (CSA) variants for product line design (PLD) are proposed.•CSAs’ performance is assessed using real and simulated data.•CSAs perform on different objectives.•The efficiency of CSAs against the state-of-the-art solvers is presented.•CSAs constitute an attractive alternative approach to the PLD problem. Product design constitutes a critical process for a firm to stay competitive. Whilst the biologically inspired Clonal Selection Algorithms (CSA) have been applied to efficiently solve several combinatorial optimization problems, they have not yet been tested for optimal product lines. By adopting a previous comparative analysis with real and simulated conjoint data, we adapt and compare in this context 23 CSA variants. Our comparison demonstrates the efficiency of specific cloning, selection and somatic hypermutation operators against other optimization algorithms, such as Simulated Annealing and Genetic Algorithm. To further investigate the robustness of each method to combinatorial size, we extend the previous paradigm to larger product lines and different optimization objectives. The consequent performance variation elucidates how each operator shifts the search focus of CSAs. Collectively, our study demonstrates the importance of a fine balance between global and local search in such combinatorial problems, and the ability of CSAs to achieve it.