Forecasting at Scale

ABSTRACT

Forecasting is a common data science task that helps organizations with capacity planning, goal setting, and anomaly detection. Despite its importance, there are serious challenges associated with producing reliable and high-quality forecasts—especially when there are a variety of time series and analysts with expertise in time series modeling are relatively rare. To address these challenges, we describe a practical approach to forecasting “at scale” that combines configurable models with analyst-in-the-loop performance analysis. We propose a modular regression model with interpretable parameters that can be intuitively adjusted by analysts with domain knowledge about the time series. We describe performance analyses to compare and evaluate forecasting procedures, and automatically flag forecasts for manual review and adjustment. Tools that help analysts to use their expertise most effectively enable reliable, practical forecasting of business time series.

KEYWORDS:

• Nonlinear regression
• Statistical practice
• Time series

Acknowledgments

The authors thank Dan Merl for making the development of Prophet possible and for suggestions and insights throughout the development. The authors thank Dirk Eddelbuettel, Daniel Kaplan, Rob Hyndman, Alex Gilgur, and Lada Adamic for helpful reviews of this article. The authors especially thank Rob Hyndman for insights connecting their work to judgmental forecasts.