In current supply chain operations, original equipment manufacturers (OEMs) procure parts from hundreds of globally distributed suppliers, which are often small- and medium-scale enterprises (SMEs). The SMEs also obtain parts from many other dispersed suppliers, some of whom act as sole sources of critical parts, leading to the creation of complex supply chain networks. These characteristics necessitate having a high degree of visibility into the flow of parts through the networks to facilitate decision making for OEMs and SMEs, alike. However, such visibility is typically restricted in real-world operations due to limited information exchange among the buyers and suppliers. Therefore, we need an alternate mechanism to acquire this kind of visibility, particularly for critical prediction problems, such as purchase orders deliveries and sales orders fulfillments, together referred as work orders completion times. In this paper, we present one such surrogate mechanism in the form of supervised learning, where ensembles of decision trees are trained on historical transactional data. Furthermore, since many of the predictors are categorical variables, we apply a dimension reduction method to identify the most influential category levels. Results on real-world supply chain data show effective performance with substantially lower prediction errors than the original completion time estimates. In addition, we develop a web-based visibility tool to facilitate the real-time use of the prediction models. We also conduct a structured usability test to customize the tool interface. The testing results provide multiple helpful suggestions on enhancing the ease-of-use of the tool.
In current supply chain operations, the transactions among suppliers and original equipment manufacturers (OEMs) are sometimes inefficient and unreliable due to limited information exchange and lack of knowledge about the supplier capabilities. For the OEMs, majority of downstream operations are sequential, requiring the availabilities of all the parts on time to ensure successful executions of production schedules. Therefore, accurate prediction of the delivery times of purchase orders (POs) is critical to satisfying these requirements. However, such prediction is challenging due to the suppliers’ distributed locations, time-varying capabilities and capacities, and unexpected changes in raw materials procurements. We address some of these challenges by developing supervised machine learning models in the form of Random Forests and Quantile Regression Forests that are trained on historical PO transactional data. Further, given the fact that many predictors are categorical variables, we apply a dimension reduction method to identify the most influential category levels. Results on real-world OEM data show effective performance with substantially lower prediction errors than supplier-provided delivery time estimates.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.