AI/ML Driven Improvement of Demand Forecasts
Stanley Black and Decker, has 60,000+ products in its portfolio and in 90+ countries. A large portfolio of products drives a robust design needs to handle a large heterogenous set of SKUs with different lifecycles, demand profiles (continuous vs discrete), zero demand events, short and long history of SKUs. With over 60K+ SKUs and 100K+ demand forecasting units planning is a compute and people intensive task and in the absence of robust methods to understand and predict demand the overhead to maintain service level can be an unseen headwind hidden as the cost of doing business. This talk will cover technical challenges related to scaling compute architecture, engineering complexity, forecasting approaches and limitations, challenges of integration of AutoML engines, challenges of architecting for future algorithm inclusion to handle the complexities of product demand heterogeneity while building a maintainable system future proofed for business continuity. Additionally, the speaker will cover the full scope of what a transformational challenge this situation provides and the operating model to implement this challenge and similar challenges in more AI/ML driven approaches. The speaker will also cover how then to use such a demand forecasting system to help drive strategic actions in Product Portfolio Management, Promotions, Pricing, Sales and Marketing to showcase an ecosystem of business decision making.
Prabhakar Narasimhadevara, Director of data science, Advanced Analytics and Data Engineering, Stanley Black & Decker (Atlanta, GA)
Prabhakar is responsible for delivery of data engineering and analytics solutions in Stanley Black & Decker organization. He has significant experience delivering analytical solutions in the healthcare, automotive, industrial distribution, industrial manufacturing, digital marketing and services industries. Many of his projects involved Machine learning, artificial intelligence, advanced analytics, architecture, strategy development and implementation, process improvement, and data lake creation.