Data Mining in TIBCO® Data Science / Statistica™ (SDM)

Summary
This training is a introduction to Data Mining using the software TIBCO Statistica™. Data Mining is very useful when large and heterogenoeous data sets are to be analyzed.
Participants are introduced to the functionalities of the software and to the most common approaches and methods and learn how to apply anlyses themselves.


Agenda

  • Data Mining: Overview
  • Predictive Models in Statistica
  • Training of Models
  • Comparison of Models
  • Deployment of Models
  • Unsupervised Learning
  • Feature Selection
  • Supervised Learning (Classification & Regression)


Type
TIBCO Statistica™ is a comprehensive, well-established and user-friendly data science software from TIBCO®. TIBCO Statistica™ is included as 'TIBCO® Data Science - Statistica®' in the software suite 'TIBCO® Data Science'. TIBCO Statistica™ will be called 'TIBCO® Data Science - Workbench®' in the future.
Our Statistica trainings offer a systematic introduction to the software. The software components and functionalities are introduced one by one and their usage is practiced with excercises. Data sets from various industries are used as examples. In our training facilites in Hamburg, each participant has access to his individual training PC to work on.
Our trainers will consider all participants question and answer them as they see fit during the training.
Training slides will be supplied to the participants as PDFs. The particpants receive all the excersises and their results after the training.


Wordcloud
Alternating Least Squares, Association Rules, AUC, Boosted Trees, C&RT, CHAID, Cluster Analysis, Clustering, CRISP, Data Driven Evaluation, EM-Clustering, Decision Trees, Misclassification Costs, k-Means, K-Nearest Neighbors, Classification, Cross-Validation, Artificial Neural Networks, Lasso Regression, Link Analysis, Logistic Regression, MARSplines, Deployment, Model Comparison, Naive Bayes, PMML, Pre-Processing, Random Forest, Recommendation, Regression, ROC, Sampling, Stratification, Support Vector Machines, Accuracy, Unsupervied Learning, Supervised Learning, Market Basket Analysis


Requirements
In order to fully benefit from the training, participants should have basic knowledge of multivariate statistics.


Duration: 2 Day(s) Price: EUR 1600 (plus VAT) per participant


Location
Hamburg: With our training facilities in Hamburg we provide a place to learn successfully in a comfortable environment. Each participant has access to a training PC there.
Online: These trainings offer high flexibility and require no traveling. Each particpant works on his own PC. We recommend the use of two monitors.
At your site: We conduct the trainings at your site for you and your colleagues.
We offer all our trainings in the languages English and German.


Please contact us!
Do you have and questions regarding the topics, the conditions or do you need a individually tailored training? Please contact us and talk directly with the involved trainers. We can surely help you!
 

Register

back to overview