Introduction to Data Mining and Predictive Analytics with RapidMiner

Thursday, Dec. 6^th and Friday, Dec. 7^th from 8:30 am to 5 pm

A light breakfast, lunch and afternoon snacks will be provided. A special dinner will be hosted by Rapid-I for all students on the Thursday night.

Class size for this event is limited to 10 students.  If the class is sold out and you wish to be added to a waiting list, contact the event organizer.

This training course is a compact two day introduction into the foundations of data mining and business analytics as well as into the software RapidMiner. After this training course the participants will have a complete understanding of how Rapid-I software works and is used. The overall data mining process is covered as well as the foundations of the software. Participants will be able to create predictive models in standard data environments typically found within most analyst positions. Due to a high number of practical exercises, the participants will be able to transfer the gained knowledge to own data mining problems and solve them quickly and easily.

After the training course the participants will have the ability to:

• perform basic data preparations
• build first predictive models,
• evaluate the model’s quality
• score new data sets

Details

• Target audience: users, analysts, developers, administrators
• Previous knowledge: basic knowledge of computer programs and mathematics
• Methods: lectures, discussions, individual and group work, exercises on realistic data.

Participants may introduce their own work and project specific questions in order to find particular solutions together with the trainer and other participants. The training course addresses beginners and intermediate learners.

Topics

• Basic Usage
• User Interface
• Creating and handling RapidMiner repositories
• Starting a new RapidMiner project
• Operators and processes
• Loading data from flat files
• Loading data from databases
• Storing data, processes and results
• Data Preparation
• Normalization and standardization
• Basic transformations of value types
• Handling missing values
• Sampling
• Filtering examples and attributes
• Handling attribute roles
• Predictive Models
• Explorative data analysis including data visualization
• Correlations
• Linear Regression
• Naïve Bayes
• Decision Trees
• Rules
• Importance of attributes
• Model Evaluation
• Splitting data
• Evaluation methods
• Performance criteria
• Lift charts
• ROC plots
• Scoring
• Applying models             

Prerequisites

You must bring a laptop to class (Windows, Mac or Linux OS is fine).  Should have Java Runtime Environment (JRE) version 1.6 (officially Java 6.0) or later installed.  Students will be provided with links to install the Community Version of RapidMiner prior to the class.

Instructor

Vijay Kotu

Vijay works in the domain of business intelligence, data mining, information design, and business analytics. With more than a decade of experience in analytics, his roles have spanned from developing enterprise wide Business Intelligence solutions, applying data mining to optimize online campaigns and performance manage large scale operations, and leading analytics program as a competency. He is currently Sr. Director of Analytics at Yahoo!

___

Classes require a minimum of 4 students by November 20 to be held.  If there are insufficient registrants, the class will be cancelled and all students will be refunded the full registration fee.  Students should organize their travel arrangements accordingly and with this proviso. Rapid-I will promptly notify registered users as soon as the 4 students quota will be met. 

___

Can't make it? Sign up for our newletter at http://rapid-i.com/content/blogsection/5/66/lang,en/ (upper left corner) to stay in the loop on future events and classes.

Our Refund Policy: Plans change? We get it. But if you can't make it to the class, please email us at training@rapid-i.com no later than November 19.  No refunds will be given after this timeframe.