What is outlier in SAP BI-RA-PA - SAP Predictive Analytics?

SAP Term: outlier

• Component: BI-RA-PA

• Component Name: SAP Predictive Analytics

• Description: An observation whose value is abnormal compared to other observations in the same dataset. An actual signal value is qualified as outlier once its corresponding forecasting error is considered to be abnormal relative to the forecasting error mean observed on the estimation dataset. The forecasting error indicator is the absolute difference between the actual and predicted values. This is also called the residue. The residue abnormal threshold is set to 3 times the standard deviation of the residue values on an estimation or validation dataset

Smart SAP Assistant

• Key Concepts: 
  Outlier is a term used in SAP Predictive Analytics to describe an observation that is significantly different from the other observations in a dataset. Outliers can be caused by errors in data entry, or they can be legitimate observations that are simply different from the rest of the data. 
  
  How to use it: 
  Outliers can be identified by using various statistical methods, such as box plots or scatter plots. Once identified, outliers can be removed from the dataset or further investigated to determine if they are valid observations. 
  
  Tips & Tricks: 
  When dealing with outliers, it is important to remember that they can be caused by errors in data entry or they can be legitimate observations. Therefore, it is important to investigate outliers further before making any decisions about them. 
  
  Related Information: 
  For more information on outliers and how to identify and deal with them, please refer to the SAP Predictive Analytics documentation.