Converting opportunities using Einstein Discovery predictive analytics

Securing opportunities, optimizing resources, and developing insights with Einstein Analytics

Leveraging CRM Analytics to focus on hot opportunities

A Fortune 500 global technology and specialty materials company headquartered in Irving, Texas, Celanese manufactures materials critical to the global chemicals, paints, and coatings industries along with Materials Solutions for automotive and consumer electronic designs. By establishing an advanced dashboard with prediction and recommendation capabilities, Celanese aspires to focus on customers with projects that have a higher chance of winning.

Prioritizing the hot deals for better guidance

Celanese needed insights into which projects (Opportunities in Salesforce) were more likely to close. They had prioritized them based on initial impressions rather than analytics, which meant that “hot” Opportunities often were overlooked and lost. Project Teams also didn’t have insights into the types of characteristics and actions that lead to a higher close likelihood. This meant that they couldn’t guide the sales team on appropriate next actions to take to help close a deal.

Providing actionable insights for better project scoring

SpringML built a Project Win Likelihood model in Einstein Discovery. The model was trained on almost three years of data and included key dimensions as selected between the SpringML and the Celanese teams. The separate Project Win models were built based on Project Segment and Industry.

Better guidance and right future steps with analytics

By analyzing the close likelihood score prescriptions in the reports, Celanese could guide the sales team on the next appropriate actions to take, and ensure that the projects with the highest close likelihood received immediate attention.