Title: Performance prediction of pharmaceutical suppliers: comparative study between DEA-ANFIS-PSO and DEA-ANFIS-GA

Authors: Rohaifa Khaldi; Abdellatif El Afia; Raddouane Chiheb

Addresses: Smart Systems Laboratory (SSL), ENSIAS College of Engineering, Rabat Information Technology Center (RITC), Mohammed V University, Rabat, Morocco ' Smart Systems Laboratory (SSL), ENSIAS College of Engineering, Rabat Information Technology Center (RITC), Mohammed V University, Rabat, Morocco ' Smart Systems Laboratory (SSL), ENSIAS College of Engineering, Rabat Information Technology Center (RITC), Mohammed V University, Rabat, Morocco

Abstract: The selection of a pharmaceutical supplier is a critical task within a hospital. Dealing with the wrong supplier may plague the overall healthcare supply chain, especially patient's life. Thereby, this study investigates the feasibility of using DEA in conjunction with ANFIS-PSO and ANFIS-GA, to evaluate and predict supplier performance. This investigation is a comparative study between ANFIS-PSO and ANFIS-GA. To our best knowledge, it fills a gap in the literature by assessing the benchmarking capabilities of the two proposed models. DEA-BCC was applied to evaluate the efficiency scores of the selected suppliers. ANFIS-PSO and ANFIS-GA were applied to learn DEA patterns and to predict the performance of unseen suppliers. Further, to determine the accuracy of those models, a statistical analysis was performed, and their results were compared with ANFIS-Hybrid model. The results revealed that ANFIS-PSO model yields the best trade-off approximation-generalisation. Thus, this model can be considered as a promising decision support system at the operational and strategic level.

Keywords: adaptive neuro-fuzzy inference system; genetic algorithm; particle swarm optimisation; data envelopment analysis; benchmarking; prediction; performance; pharmaceutical suppliers; healthcare supply chain.

DOI: 10.1504/IJCAT.2019.101172

International Journal of Computer Applications in Technology, 2019 Vol.60 No.4, pp.317 - 325

Received: 02 Jun 2017
Accepted: 20 Feb 2018
Published online: 26 Jul 2019 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article