Predictive ML - How Unilever is Improving its Forecasting

Discover how Unilever is revolutionizing its forecasting processes in this 29-minute conference talk by Bill Tsiligkiridis, Europe Data Science Lead at Unilever. Learn about the implementation of machine learning predictive models to forecast key business metrics at various levels of granularity. Explore the reusable predictive framework developed on the Databricks Platform, designed to enhance and automate forecasting processes. Gain insights into the framework's components, including data preparation, feature engineering and selection, ML and statistical model training and deployment, prediction generation, explainability, performance monitoring, and evaluation. Understand how this innovative approach aims to improve existing manual forecasts and fill gaps where manual predictions are unavailable, ultimately leading to more robust and efficient business forecasting.