Child pages
  • EI Data Mining Methods
Skip to end of metadata
Go to start of metadata

Data mining methods available with SAP:

  • Decision Trees
  • Clustering
  • Association Analysis
  • Scoring
  • Weighted Score Tables
  • ABC Classification

Decision Trees

Used as a predicive model which maps observations about an item to conclusions about the item's target value. It describes the data but not the decisions. The resulting decision tree can be used for decision making.  In SAP, decision trees display data using (non-continuous) category quantities. The display rules are determined in training using those sections of historic data where the assignment to categories is already known.


The task of assigning a set of objects into groups or clusters so that similar objects are grouped together based on their similarity is called clustering. In the same cluster, each object has some set relationship to each other which is identifiable. In SAP, clustering is used to split data into homogeneous groups. The model looks for a global structure for the data with the aim of partitioning the data into clusters.

Association Analysis

This is a method for discovering interesting relationships between variables in large databases. Generally, the order of the items is not taken into consideration. In SAP, this type of data mining can be used to establish composite effects and thereby identify cross-selling opportunities, for example. The search for associations considers objects with information content that is remotely comparable. Statements are formulated about partial structures in the data and take the form of rules. In contrast to decision tree classification, clustering and association analysis determine the models using the data itself.


Generally this term is used to describe the ranking of the models so that the user can determine a score which rates the usefulness of each model. In SAP, the data is displayed using continuous quantities. If required, discretisation can then be applied to split the data into classes. The scoring function can either be specified using weighted score tables or be determined by training using historic data as linear or nonlinear regression of a target quantity.

Weighted Score Tables

Analysing data and then rating it after applying a weighting to the data so that the predictive results are not as obscure as could be returned. The weighting is held in table format to be used again.

ABC Classification

Making use of a categorisation technique which determines that the data (usually inventory) is not all equal in importance. There are no fixed threshold for each class, different proportion can be applied based on objective and criteria. In SAP, data is grouped into classes of A, B, C and so on, using thresholds and classification rules.  The classified results are displayed in the form of ABC chart or list. You can use historic data to train the models that you create for these data mining methods. This data helps the model to learn by establishing formerly unrecognized patterns. You can either export the result of this learning process into another system (association rules) or you apply the result during prediction to other data that lacks certain information (clustering, decision trees). You use BW queries to train the model and perform the prediction. You assign these BW queries to the model as sources for the respective business transaction.