When Data Science Becomes an Art: Forecasting when Historical Data Is Irrelevant
2020’s word of the year is likely to be “unprecedented” — which might make us rather nervous as data scientists or analytics professionals. Machine learning is, after all, the art and science of predicting outcomes of upcoming events based on historical data; in a period without precedent, most available data describes a different, bygone world. In this session, we discuss how this affects our ability to build useful predictive analytics models for the current environment and how to ensure that data science and machine learning continue to add business value. We discuss the concept of system change, look at how to identify it and deal with it if necessary, and explore strategies to adapt the data science process to abnormal modeling environments.
Session ID: Presentation Type: On-Demand Session (Recorded)
Date / Time: [Educational] @ On Demand ET (US)
Presented by:DataRobot is the leader in enterprise AI, delivering trusted AI technology and ROI enablement services to global enterprises. DataRobot’s enterprise AI platform democratizes data science with end-to-end automation for building, deploying, and managing machine learning models. Click for more details and additional sessions and content.
To view this session, register for the conference.