Automatically detect and correct outliers in time series data.

The automatic outlier correction preprocessing algorithm uses machine learning to automatically detect and correct outliers in time series data before forecast calculations are run. An outlier is a value in the historical data that lies outside the accepted range of values, which is also called the tolerance lane. There can be a variety of reasons for this deviation; for example, a data entry error or a one-time event that affected the sales results. Outliers may occur in any time series. If they are treated as if they were regular values, they may skew the forecast calculations. The automatic outlier correction algorithm prevents this by automatically detecting and correcting outliers in the time series before forecasting is executed. You can add the algorithm to your forecast model on the Preprocessing Steps tab of the Manage Forecast Models app.