Forecasting at the speed of modern retail

Summary

Retail and CPG forecasting now spans hundreds of thousands, sometimes far more, time series across fragmented channels, promotions, and short-lived products, making legacy methods and manual exception management difficult. Multi-model forecasting addresses this complexity by evaluating a range of techniques against actual data and selecting the best-performing model for each series, but enterprise-scale experiments require scarce forecasting and distributed-systems expertise. Released in 2024, Databricks’ open-source Many Model Forecasting (MMF) integrates more than 35 statistical, deep-learning, and foundation time-series models and runs on distributed Databricks compute. MMF Agent, built on Genie Code, guides users through data quality, series classification, compute configuration, forecasting, post-processing, and model selection, while Unity Catalog helps it use organizational data context. The workflow is intended to reduce setup from days to hours, improve targeting and accuracy, and make rigorous forecasting more accessible while remaining customizable for technical teams.

Context

Retail and CPG organizations face forecasting environments with hundreds of thousands or more time series, increased channel and regional fragmentation, short-lifecycle promotional SKUs, and external influences such as promotions, weather, and macroeconomic conditions. Legacy tools, manual exception management, and scarce combined forecasting and distributed-systems expertise make rigorous multi-model experimentation difficult and slow.

Approach / What changed

MMF Agent wraps Databricks’ Many Model Forecasting framework in a guided workflow built on Genie Code. It checks and prepares data, classifies time series, configures distributed compute, runs forecasting jobs, performs post-processing and model selection, and connects recommendations to business outcomes. Its Unity Catalog integration provides context about organizational data, while access to MMF source code and skills supports customization.

Takeaways

• MMF integrates more than 35 statistical, deep-learning, and foundation time-series models and automatically selects the best-performing model for each time series.
• MMF Agent adds data-quality checks and time-series classification before forecasting, directing computation toward forecastable series and supporting better-targeted model selection.
• The guided workflow is designed to compress setup and experimentation from days to hours and broaden access to multi-model forecasting beyond specialist data-science teams.

Related reading