Stochastic programming for vendor portfolio selection and order allocation under delivery uncertainty

Outsourcing has been employed in supply chain management to reduce capital investment, enhance flexibility, reduce manufacturing cost, shorten cycle time, and improve service quality. This study aims to propose a portfolio optimization model considering risk diversification and delivery uncertainty for vendor portfolio selection and order allocation. Three portfolio objectives for maximizing performance of selected vendors, diversifying the portfolio risk, and minimizing total cost are considered. A comparison of two proposed stochastic programming techniques shows that robust optimization can generate a better solution whereas probabilistic models can identify the potential alternative vendor based on a data-driven approach. An application study was conducted in a leading semiconductor company in Taiwan to estimate the validity of the proposed approach. The results have shown practical viability that the proposed approach can generate the results with better vendor performance, diversified risk, and minimal total cost.