Ternopil Ivan Puluj National Technical University

Каф. комп'ютерних наук

Data Mining


1. Educational programs for which discipline is mandatory:

# Educational stage Broad field Major Educational program Course(s) Semester(s)
1 bachelor's 12. Інформаційні технології 122. Комп’ютерні науки та інформаційні технології (бакалавр) 1 1

2. The course is offered as elective for all levels of higher education and all educational programs.

3. Information about the author of the course

Full name Козбур Галина Володимирівна
Academic degree none
Academic title none
Link to the teacher`s page on the official website of the University
Е-mail (in the domain

4. Information about the course

Study hours structure Lectures: 16
Practical classes: 0
Laboratory classes: 32

Amount of hours for individual work: 0
ECTS credits: 4
Teaching language english
Form of final examination credit
Link to an electronic course on the e-learning platform of the university

5. Program of discipline

Description of academic discipline, its goals, subject of study and learning outcomes

The purpose of the study is for students to master modern methods, tools and technologies of data processing, search in large data sets of practically useful knowledge and patterns necessary for business and other decisions, the ability to analyze data and present the results of such analysis.

The place of academic discipline in the structural and logical scheme of study according to the educational program

Prerequisites. List of disciplines, or knowledge and skills, possession of which students needed (training requirements) for successful discipline assimilation

Students must have basic knowledge of higher mathematics, probability theory and mathematical statistics, programming, theory of algorithms.

Contents of the academic discipline

Lectures (titles/topics)

1. Introduction to Data Mining. Stages, models, methods of Data Mining. The main tasks. Data, their types.
2. Statistical methods of numerical data processing. Types of data distributions. Box charts.
3. Fundamentals of machine learning. The problem of classification. Decision tree as a classifier. Criteria for division into classes. Algorithm retraining. Metric methods of classification. Quality metrics of classifiers. Solutions tree ensembles.
4. The problem of clustering. Iterative and hierarchical methods of clustering. Types of metrics. Clustering model validation techniques.
5. The regression problem. Single-factor and multiple regressions. Quality metrics for the regression model. Multicollinearity of signs.
6. Data visualization. Basic rules of infographics. Basic concepts of graphic design. Time series and their application. Trends.

Laboratory classes (topics)

#1. Data Analysis in Spreadsheets
#2. Intermediate Spreadsheets
#3. Pivot Tables in Spreadsheets
#4. Data Visualization in Spreadsheets
#5. Python Data Science Toolbox (Part 1)
#6. Python Data Science Toolbox (Part 2)

6. Policies and assessment process of the academic discipline

Assessment methods and rating system of learning results assessment

The form of the final semester control is a credit.
The final semester grade consists of the sum of points obtained for laboratory work.
The points earned for the semester are automatically multiplied by 4/3.

Table of assessment scores:

Assessment scale
(100 points)
(4 points)
90-100 Excellent А
82-89 Good B
75-81 C
67-74 Fair D
60-66 E
35-59 Poor FX
1-34 F
Approved by the department
(protocol №
on «