Leveraging Predictive Analytics in the Supply Chain: Pairing Best of Breed and ERP

Making timely decisions based on relevant, available data is crucial to business success, yet a high number of companies still rely on historical information to steer their decision-making. Others are tapping into the value of predictive analytics - the use of statistics, modeling, machine learning, and data mining to analyze current and historical facts and make future predictions - to manage various aspects of their supply chains and logistics operations.

Predictive analytics have already proven their worth on several fronts. In Revising an Outdated Business Model? Try Predictive Analytics, for example, the author discusses how sensors were monitoring a Swiss airliner's engines during a recent trans-Pacific flight. Those sensors were sending back data to the offices of an analytics provider that, at one point when the airliner was over the ocean, realized that there was an engine problem. Thanks to predictive analytics, the pilot was able to take fast action and landed the aircraft safely and without incident.

Not all instances of predictive analytics in the supply chain are as dramatic as this in-air example, but their usage is definitely growing across many industries. Ann Grackin, CEO at ChainLink Research, says that more companies are catching onto the value of predictive analytics in the supply chain. Armed with reams of historical data, ERP users are well positioned to begin using the information gathered to make better, more informed supply chain decisions in the future.

Unfortunately, the historical supply chain data generated by systems like Microsoft Dynamics AX don't tell companies what's impending or looming on the horizon. "They also don't help companies when it comes to new areas of inquiry," Grackin points out, "such as understanding ...