Techniques are provided for determining a delay in a data process flow at an enterprise data warehouse. An example method includes a device receiving historical data from a staging area and a target database of a data warehouse. The device can generate a feature for a machine learning model based at least in part on the historical data. The device can generate a forecasted time interval between receipt of data at the staging area and receipt of the data at the target database using the machine learning model and based at least in part on the generated feature, the data to be transmitted from the staging area to the target database. The device can compare the forecasted time interval with an expected time interval. The device can generate a work ticket based at least in part on the comparison.