A hybrid approach using data envelopment analysis and artificial neural network for optimising 3PL supplier selection

Today third party logistics (3PL) service providers are into almost all the businesses right from providing raw material to packaging. 3PLs are also getting involved in customers concerned with operations. At a suitable price and consideration of all affecting criteria, anything can be outsourced. Any exporter needs to find a smart balance of what to perform in-house and what to hire outside providers to do (i.e., increase verticals and reduce horizontal supply chain operations). Thus, the demand of 3PL provider has become an important issue for organisations seeking quality customer service and cost reduction. The current research presents an integrated data envelopment analysis (DEA) and artificial neural networks (ANN) methodology for the evaluation and selection of 3PL providers. DEA is employed to identify the maximally efficient 3PL and to eliminate the unsuitable ones; and, ANN to rank and make the final selection. The proposed method enables decision makers to better understand the complete evaluation and selection process of 3PL selection. Furthermore, this approach provides a more accurate, effective, and systematic decision support tool for 3PL selection. Finally, an actual industrial application is presented to demonstrate the proposed method.