Workshop on

DATA MINING: PRACTICAL TOOLS AND TECHNIQUES

8th - 11th February, 2010

Organized by

Open and Distance Learning Centre at
The Faculty of Electrical Engineering and Information Technologies
and
TIME.mk Education

FINISHED !!!

Description
Schedule
Lecturer
Registration and fees
Contact

Description

Data mining (DM) is the process of extracting patterns from data. Technology now allows us to capture and store vast quantities of data. Finding patterns, trends, and anomalies in these datasets, and summarizing them with simple quantitative models, is one of the grand challenges of the information age—turning data into information and turning information into knowledge. The synthesis of statistics, machine learning, information theory, and computing has created a solid science, with a firm mathematical base, and with very powerful tools.

This workshop will present DM in a very accessible form: as a introduction to the next generation of practitioners and researchers. Four classical types of DM tasks will be covered:

Classification - Arranges the data into predefined groups. For example an email program might attempt to classify an email as legitimate or spam. Common algorithms include Decision Tree Learning, Nearest neighbor, naive Bayesian classification and Neural network.
Clustering - Is like classification but the groups are not predefined, so the algorithm will try to group similar items together.
Regression - Attempts to find a function which models and predicts numerical data with the least error.
Association rule learning - Searches for relationships between variables. For example a supermarket might gather data on customer purchasing habits. Using association rule learning, the supermarket can determine which products are frequently bought together and use this information for marketing purposes. This is sometimes referred to as "market basket analysis".

Also, introduction and real-life application of the DM software WEKA will be presented.

Prerequisite:
Basic knowledge of data structures, algorithms and probability.

Language:
All materials (slides, codes, etc.) will be provided in English language but the lectures will be taught in Macedonian language.

Learning outcomes:
On completion of this workshop, you should be able to:

Understand the theoretical underpinnings of the main data-mining algorithms.
Assess raw input data, and process it appropriately to provide suitable input for a range of data mining tools (algorithms).
Critically evaluate and select appropriate data-mining tool (algorithm, model) and be able to apply them and interpret and report the output appropriately.

Schedule

	Date / Time	Title	Description
Lecture 1	8 February, 2010 / 18:15h-19:15h	What’s it all about?	Data mining and machine learning, Simple examples, Machine learning and statistics, Generalization as search
Lecture 2	8 February, 2010 / 19:30h-20:30h	Input: Instances and Attributes ---> Output: Knowledge representation	What’s a concept?, What’s in an example?, What’s in an attribute?, Decision tables, Decision trees, Classification rules, Association rules, Trees for numeric prediction, Instance-based representation, Clusters
Lecture 3	9 February, 2010 / 18:15h-19:15h	Algorithms: The basic methods - Part 1	Inferring rudimentary rules, Constructing decision trees, Constructing rules, Mining association rules
Lecture 4	9 February, 2010 / 19:30h-20:30h	Algorithms: The basic methods - Part 2	Linear models, Instance-based learning, Clustering
Lecture 5	10 February, 2010 / 18:15h-19:15h	Credibility: What’s been learned ?	Training and testing, Predicting performance, Cross-validation, Comparing data mining methods, Evaluating numeric prediction
Lecture 6	10 February, 2010 / 19:30h-20:30h	Transformations: Engineering the input and output	Attribute selection, Discretizing numeric attributes, Combining multiple models, Using unlabeled data
Lecture 7	11 February, 2010 / 18:15h-19:15h	Introduction to Weka (part I)	Filtering algorithms, Learning algorithms, Clustering algorithms, Association-rule learners
Lecture 8	11 February, 2010 / 19:30h-20:30h	Introduction to Weka (part II)	Metalearning algorithms, Distributing processing over several machines

Lecturer

Dr. Igor Trajkovski graduated from the Institute of Informatics, Faculty of Natural Sciences and Mathematics, Ss. Cyril and Methodius University - Skopje, in 2001. In 2004 he obtained Master of Computer Science at Max Planck Institute for Informatics, Saarbrucken, Germany. His studies and research work has continued on Jozef Stefan Institute in Ljubljana, Slovenia in the Department of Knowledge Technologies, where in 2007 gains the academic title Doctor of Sciences. In 2007-2008 he worked for Google (Mountain View, California, USA and Zurich, Switcerland) as software engineer and software engineer in testing. He is the founder of the Macedonian and Slovenian news aggregators TIME.mk and TIMES.si and TIME.mk's branch for life-long continuous education, TIME.mk Education. His research interests include: Statistical Natural Language Processing, Machine Learning, Advanced Algorithms and Data Structures, Parallel Algorithms, Bioinformatics.

Registration and fees

The workshop tuition, 10200 MKD (6800 MKD for undergraduate students - proof required) includes four days (8 lectures) of presentations and learning. You will also receive take-home comprehensive reference material. The minimal (maximum) number of attendees is 10 (30). The offer is on a first-come-first-served basis, according to the payment of the workshop tuition.

First and Last Name:
Email address:
Status:
Comments:

PP 50 for tuition payment	Venue of the event

For larger image, click on it

Certificates of Attendance, issued by ODLC at FEIT and edu.TIME.mk, will be awarded to students who will attend at least 6 of the 8 lectures.

Contact

If you have additional questions concerning the workshop, you can ask Dr. Igor Trajkovski (email: admin@time.mk).