Data Mining in the ML and Statistics Community

In this ML Pipeline we go from a data input to Data Preparation which includes:

• Data Integration
• Normalization
• Feature Selection
• Dimensionality Reduction
• Data Cleaning
• Data Discretization
• …

Now we can get to the Data Mining part of the pipeline which includes:

• MOC - Pattern Recognition
• Correlation Analysis
• Classification
• Clustering
• KDD Chapter 9 Outlier Analysis
• Linear Regression / Regression

Now as one of the last steps we have post processing which includes:

• Pattern Evaluation
• Selection
• Interpretation
• and important: Data Visualization

And all of the work done in the pipeline will result in some useful information or knowledge that was gained from the data.