Direct Channel Demand Planning (Fortune 100 Technology Company)
Download as PPTX, PDF0 likes877 views
The document discusses a case study on improving forecast accuracy in the direct channel for a Fortune 100 technology company, achieving a 17% increase. It highlights the use of data analysis and forecasting models tailored to customer specifications over a three-month client project period, resulting in approximately 80% adoption by demand planners. The study emphasizes the importance of algorithm development to better identify patterns in direct customer bookings amid a competitive landscape.
1 of 1
Downloaded 18 times
More Related Content
What's hot (20)
Ad
Viewers also liked (20)
Ad
Similar to Direct Channel Demand Planning (Fortune 100 Technology Company) (20)
More from BRIDGEi2i Analytics Solutions (20)
Recently uploaded (20)
Direct Channel Demand Planning (Fortune 100 Technology Company)
- 1. A Case Study in Direct Channel Demand Planning A Fortune 100 Technology Company Quick Context Objective • 17% higher forecast accuracy in the Direct Channel • Insights on how different Direct Customers order products Impact • BRIDGEi2i specializes in a vast array of forecasting applications • Our knowledge of key forecasting aspects enables us to quickly identify the root-cause issues and address them analytically Key Success Elements Our Approach 3 Months 3 Years Client Project length Length of relationship with client • Data was securely accessed and handled within client environment • Order data was accessed for specific Customer attributes and Model-Option information • Historical Bookings data was used to identify Customer-SKU associations • All analysis was done in Client SAS environment • Segmentation based on Coefficient of variation for product ids exhibiting similar volatility structure • Medium and High contributors were treated with ensemble forecasting models • Monthly seasonal profiling were obtained at product family level and was imposed on each product • A rigorously tested code was developed and validated repeatedly on historical Bookings prediction accuracy • The final SAS code would fetch data from Teradata, Order Data and historical Bookings, Identify and flag Direct Bookings in Demantra • Model has yielded great results; ~80% adoption by Demand Planners Data Management Algorithmic Play Operationalization a. ~12,000 SKUs are sold solely through the Direct Channel; very volatile and cyclical demand b. Short product lifecycles and highly competitive landscape a. To develop an algorithm that identifies patterns in Direct Customer bookings b. To develop a unique forecasting model for just Direct customers