In this webinar recording, you’ll learn from DataRobot’s Chief Scientist Michael Schmidt how companies use machine learning to solve critical time series problems like optimizing staffing levels, managing inventory, forecasting future product demand, and more.
The goal of time series modeling is to predict future performance from past behavior for time-dependent data – such as forecasting sales over a holiday season, predicting how much staff you need for the upcoming week, or ensuring inventory meets manufacturing demands without overstocking.
Time series modeling is complex and laborious because of the number of historical events that impact the current predictions, making it difficult to find the most influential signals in the data. As conditions change – such as a new product introduction or a competitor opening a new store – these models need to be re-built. Until now.
DataRobot Time Series integrates best practices in time series modeling, including automating time series feature engineering to discover predictive signals. It also automatically detects stationarity, seasonality, transforms the target, and implements backtesting to achieve the highest possible accuracy.
Beyond essential and proven times series methods like ARIMA and Facebook Prophet, DataRobot Time Series includes advanced time series models that help you achieve even higher forecasting accuracy.
Since the goal of a time series model is to both extract understanding and predict future outcomes, DataRobot Time Series offers many ways to visualize insights over time and to deploy models to production - including full API support to integrate modeling into business processes and applications.
We have data – a lot of data – and we want to use it to our advantage. DataRobot has the tools to help us take historical data, manipulate it, and learn from it. We’ve already experienced tremendous cost and time savings with DataRobot, and these latest advancements will further transform how we forecast nurse staffing and patients’ length of stay—both of which will yield significant benefits for our hospital network.
The Executive Director of Information Systems and Software Development at Steward Health Care
Steward Health Care, the largest for-profit private hospital operator in the United States, is using DataRobot’s to significantly improve operational efficiency and reduce costs among their network of 38 hospitals across the nation. Sixty percent of hospital operations expenses come from staffing alone.
With DataRobot’s improved forecasts for patient volume, Steward’s potential labor savings amount to $2 million by reducing hospital overstaffing by 1% for just eight of the 38 hospitals in Steward’s network.
"Time series machine learning has historically resisted automation. Having worked with DataRobot’s time series product for the past several months, including delivering real financial applications, I’m amazed at what is possible and how easily models can be built."
Professor of Business Administration and Faculty Chair, Harvard Business School