The course “Data Mining with R”, which takes place from 9th to 10th November 2015 in Kassel, Germany, teaches the most important methods to expose correlations in data and inherent patterns.
The wide set of methods can be used for almost every application area. From customer segmentation to timely recognition of machines, users gain knowledge from data and therefore advantages in competition because of the right use of methods.
By means of practical examples, the following topics will be addressed:
- Introduction to Data Mining
- Evaluation model: Selection of model and data base, error matrix, risk charts, ROC, sensitivity, precision, Lift, forecast and observation
- Explorative Analysis: Tabular analysis, visual analysis (metric, categorical), correlation analysis, Missing value correlation
- Association Analysis: Support, confidence, Lift, interpretation
- Regression- and Decision Trees: Algorithm, interpretation, graphical interpretation
- Neural Networks: Theory, learning process in KNN, nnet
- Random Forest: Theory, interpretation, extended options, Conditional inference trees
“Data Mining with R” shows the creation of Data Mining scripts and teaches how to use the graphical user interface “Rattle”. After the course, participants are able to apply what they have learnt for their own application purpose.
For more information about our training program and the application form feel free to click here.