Use Intel® oneAPI Libraries to Optimize a Demand-Forecasting Solution
The Tiger Demand-Forecasting solution helps companies rapidly deploy the AI engine at scale. It delivers value by generating accurate forecasts and enabling better planning and running. The solution is enabled for consumer product companies across sectors including:
- Food and beverages
- Personal and household products
- Durables and appliances
- Quick-service restaurant (QSR)
This complete white-box solution meets the challenges of forecasting in a dynamic environment while addressing complexities around client product hierarchies and business scale. It facilitates integration into planning tools like SAP, Integrated Business Planning (IBP), O9*, OMP, and more.
This discussion addresses the benefits of using libraries in Intel® oneAPI (like oneAPI Deep Neural Network Library and oneAPI Math Kernel Library) to optimize the Tiger Demand-Forecasting Solution using the Apache MXNet* framework. It also touches on some of the challenges faced during this project and they were overcome to adopt libraries from Intel oneAPI.
Accelerate deep learning frameworks on Intel® architecture with these highly vectorized and threaded building blocks for implementing CNNs with C/C++.
Product and Performance Information
Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.