https://community.databricks.com/t5/data-engineering/how-to-use-databricks-feature-store-for-time-series-forecasts/m-p/21972#M15002 <P>I've seen the Databricks documentation on time series <A href="https://docs.databricks.com/applications/machine-learning/feature-store/time-series.html" alt="https://docs.databricks.com/applications/machine-learning/feature-store/time-series.html" target="_blank">here</A>. I'm using forecasts as a feature and those forecasts have both an as-of timestamp (when the forecast was generated) and a time step label (timestamp indicating the time of the forecasted observation).</P><P></P><P>Schema:</P><P>as_of_timestamp</P><P>observation_timestamp</P><P>value</P><P></P><P>Does anyone have thoughts on how best to structure this kind of data? Specifically, I'm wondering about how to specify the primary and timestamp keys when creating the feature.</P> Wed, 27 Apr 2022 16:06:04 GMT rgrosskopf 2022-04-27T16:06:04Z https://community.databricks.com/t5/data-engineering/how-to-use-databricks-feature-store-for-time-series-forecasts/m-p/21972#M15002 <P>I've seen the Databricks documentation on time series <A href="https://docs.databricks.com/applications/machine-learning/feature-store/time-series.html" alt="https://docs.databricks.com/applications/machine-learning/feature-store/time-series.html" target="_blank">here</A>. I'm using forecasts as a feature and those forecasts have both an as-of timestamp (when the forecast was generated) and a time step label (timestamp indicating the time of the forecasted observation).</P><P></P><P>Schema:</P><P>as_of_timestamp</P><P>observation_timestamp</P><P>value</P><P></P><P>Does anyone have thoughts on how best to structure this kind of data? Specifically, I'm wondering about how to specify the primary and timestamp keys when creating the feature.</P> Wed, 27 Apr 2022 16:06:04 GMT https://community.databricks.com/t5/data-engineering/how-to-use-databricks-feature-store-for-time-series-forecasts/m-p/21972#M15002 rgrosskopf 2022-04-27T16:06:04Z