MIT report examines predictive analytics in supply chains

MIT’s Center for Transportation and Logistics (CTL) has released a summary report of a recent roundtable discussion on predictive analytics in supply chain, officials said.

The virtual roundtable was held last fall for CTL’s Supply Chain Exchange Partners and featured presentations by academics and industry experts on the challenges and opportunities for using predictive analytics in the supply chain. The subsequent report was made available for download this month.

The report summarizes key concepts and the main algorithmic methods for doing predictive analytics, and explains how participants are using the technology in supply chain operations. Demand forecasting, predicting the timing of events (driver availability, container unloading, and shipment events, for example), and anomaly risk prediction (manufacturing scrap rates, anomalous orders, and service failures) are among the applications participants cited. Forecasting was the most prevalent application, with 70% of participants saying they use predictive analytics for that reason.

Participants also listed some common obstacles to implementing predictive analytics, including data availability, organization maturity, and alignment of data science projects to organizational needs.

For more information, visit the CTL website.