cancel
Showing results for 
Search instead for 
Did you mean: 

Automated Time Series vs. OTV

Highlighted
Image Sensor

Can someone please explain the difference between Automated Time Series and OTV? I understand they’re both time-aware models, but how do they compare and which might I want to use?

Labels (1)
1 Reply
Highlighted
DataRobot Alumni

Good question. You'll want to use Automated Time Series when you want to forecast multiple future values of a target (for example, when predicting sales for each day next week). Automated Time Series will extrapolate future values in a continuous sequence.

In comparison, you'll use Out-of-Time Validation (OTV) when your data is time-relevant, but you are NOT forecasting (e.g., you are predicting the target values for data that fits on individual rows). Use this if you have single event data, such as patient intake or loan defaults.

I hope that answers your question.