•   Exclusive

Achieving better outcomes for predictive analytics

A deeper understanding of the technology will help practitioners and business leaders make clearer connections between needs and model outputs—and hence frame better questions.

Subscriber: Log Out

Sorry, but your login has failed. Please recheck your login information and resubmit. If your subscription has expired, renew here.

This is an excerpt of the original article. It was written for the January-February 2021 edition of Supply Chain Management Review. The full article is available to current subscribers.

January-February 2021

This morning, I turned on the television and watched the first stretch-wrapped pallets of the just-authorized vaccine being loaded onto a truck at a Pfizer plant in Michigan. From there, the pallets were headed to FedEx’s logistics hub in Memphis where they would be delivered to 153 locations across the 50 states. The event was both historic and mundane: Historic in that the shipments represent the hope of a nation that in the coming months, we’ll begin to put 2020—and COVID—in the rearview mirror; mundane in that this is a scene repeated millions of times a day, without fanfare, in plants and distribution centers across the country. Two of…
Browse this issue archive.
Already a subscriber? Access full edition now.

Need Help?
Contact customer service
847-559-7581   More options
Not a subscriber? Start your magazine subscription.

Predictive analytics enable supply chain practitioners to anticipate business outcomes—providing they ask the right questions of the technology.

Framing appropriate questions requires professionals to identify the issues that need to be explored, and to understand what can and cannot be modeled using predictive analytics. This combination of business and technical know-how is not always available, however.

Challenges like this were discussed by practitioners and data scientists from a broad range of companies at MIT CTL’s Analytics of the Future Roundtable: Predictive Analytics on November 18, 2020. Enterprises at different stages of development described their approaches to harnessing the predictive power of analytics.

Horses for courses

Understanding the technology’s alchemy can be a stumbling block for executives when deciding which use cases or ideas they want to model. There are four or five types of predictive models commonly used in supply chain applications, and each one has quirks that align it with certain types of problems. Knowing these differences in advance helps to refine the search for use cases and avoid presenting data analytics teams with projects that turn out to be impractical and time-wasting.

This complete article is available to subscribers only. Log in now for full access or start your PLUS+ subscription for instant access.

SC
MR

Sorry, but your login has failed. Please recheck your login information and resubmit. If your subscription has expired, renew here.

From the January-February 2021 edition of Supply Chain Management Review.

January-February 2021

This morning, I turned on the television and watched the first stretch-wrapped pallets of the just-authorized vaccine being loaded onto a truck at a Pfizer plant in Michigan. From there, the pallets were headed to…
Browse this issue archive.
Access your online digital edition.
Download a PDF file of the January-February 2021 issue.

Download Article PDF

Predictive analytics enable supply chain practitioners to anticipate business outcomes—providing they ask the right questions of the technology.

Framing appropriate questions requires professionals to identify the issues that need to be explored, and to understand what can and cannot be modeled using predictive analytics. This combination of business and technical know-how is not always available, however.

Challenges like this were discussed by practitioners and data scientists from a broad range of companies at MIT CTL’s Analytics of the Future Roundtable: Predictive Analytics on November 18, 2020. Enterprises at different stages of development described their approaches to harnessing the predictive power of analytics.

Horses for courses

Understanding the technology’s alchemy can be a stumbling block for executives when deciding which use cases or ideas they want to model. There are four or five types of predictive models commonly used in supply chain applications, and each one has quirks that align it with certain types of problems. Knowing these differences in advance helps to refine the search for use cases and avoid presenting data analytics teams with projects that turn out to be impractical and time-wasting.

SUBSCRIBERS: Click here to download PDF of the full article.

SC
MR

Latest Podcast
Talking Supply Chain: Lexmark’s missing piece
In need of supply chain visibility, Lexmark looked within and built a tool that is helping it identify potential issues before they occur. Billy…
Listen in

Subscribe

Supply Chain Management Review delivers the best industry content.
Subscribe today and get full access to all of Supply Chain Management Review’s exclusive content, email newsletters, premium resources and in-depth, comprehensive feature articles written by the industry's top experts on the subjects that matter most to supply chain professionals.
×

Search

Search

Sourcing & Procurement

Inventory Management Risk Management Global Trade Ports & Shipping

Business Management

Supply Chain TMS WMS 3PL Government & Regulation Sustainability Finance

Software & Technology

Artificial Intelligence Automation Cloud IoT Robotics Software

The Academy

Executive Education Associations Institutions Universities & Colleges

Resources

Podcasts Webcasts Companies Visionaries White Papers Special Reports Premiums Magazine Archive

Subscribe

SCMR Magazine Newsletters Magazine Archives Customer Service

Press Releases

Press Releases Submit Press Release