Combined application of logistic regression and the analytic hierarchy process to the supplier selection problem

Abstract

An approach to supplier selection for retail enterprises is proposed. When a large number of alternatives exists, applying T. Saaty's Analytic Hierarchy Process (AHP) directly to the entire set becomes labor-intensive and lacks sufficient informativeness. Therefore, the first stage involves constructing a logistic regression model to perform an initial filtering of alternatives, which helps ensure commercial success. Subsequently, a modified version of Saaty's method is used to rank the remaining suppliers based on their integral utility