Fuzzy c-means clustering-based key performance indicator design for warehouse loading operations

Abstract Performance measurements are important motivators in evaluating a company’s strategy. The performance improvement process starts with the measurement of the current situation. Therefore, companies use various metric quantities for the efficiency and productivity of warehouse management. Recently, many studies have been conducted on key performance indicators. In this study, an artificial intelligence-aided key performance indicator is intended for the loading performance of a warehouse, and the analysis is performed based on various scenarios. In the pre-processing phase, five inputs are taken as the unit price, monthly demand quantities, the number of products loaded from the warehouse, the demand that cannot be loaded on time, and the average delay times of the products that cannot be loaded on time. The outputs of the pre-processing phase are clustered using a fuzzy c-means clustering algorithm. Then a key performance indicator for the warehouse loading operations is proposed using the fuzzy c-means clustering result. Researchers and engineers can easily use the proposed scheme to achieve efficiency in warehouse loading management.