Supplier Selection using Multi Criteria Decision Making (MCDM) Models and Random Forest Algorithm

Supplier Selection using Multi Criteria Decision Making (MCDM) Models and Random Forest Algorithm

Sruthi Sreekumar, Neelapa Reddy Sanjana, Shreya Nahar, Indumathy M

Abstract — Supplier Selection plays a crucial part in Supply Chain Management. The issues with inefficient supplier selection has been an emerging issue in the industry making it necessary for a solution to be discovered. Great academicians and industrialists brought in the concept of Multi-Criteria Decision Making (MCDM) methods for effective supplier selection. These approaches can be used for small scale analysis and selection where the recent performance of the company is used as the criterion for the selection. However, the complexity of such approaches may increase significantly, especially when considering the performance of the suppliers from past few years as the criteria for supplier selection. To address this problem, we have used the Random Forest Algorithm (RF). The applicability of the approach is demonstrated using data from Textile Industry Supplier Performance from the past 5 years. Results show that Random Forest can successfully lead to an effective supplier selection, which would lead to a less complex but efficient application of Supplier Selection.

Keywords—supplier selection, MCDM, Machine Learning, Random Forest