ITEC4433 - Data Warehousing and Data Mining

ITEC4433 - Data Warehousing and Data Mining
Semester: 2021 Fall

Type: 100% Online
Level of Course: Undergraduate
Language of Instruction: English
Prerequisite: UG-JUNIOR, UG-SENIOR
Class hours: ThThTh123
Instructor: Dr. Gülsüm Çiğdem Çavdaroğlu cigdem.cavdaroglu@isikun.edu.tr
Course Description: In this course, the fundamentals of data mining are explained. As a result of the
growing interest in Data Science Techniques, studies on the extraction of
information from the data have also accelerated. Thanks to the Data Mining
algorithms, Computable Paradigms and Computers, extracting information
from databases and recognizing patterns are possible today. With the
development of technology, the performance of these processes has increased.
When the indicators are analyzed, it is seen that the Data Mining concept has
become very important today. It can be predicted that it will maintain its
importance in the coming years. In the process of data science, which is a long
journey, Data Warehousing and Data Mining course can be considered as the
first step.
Course Objectives: In this course, it is aimed to teach the fundamentals of Data Mining. It is aimed
to explain the basic functions and models used in Data Mining, to explain and
use the algorithms for these functions and models. To reinforce the theoretical
and technical information to be given in the course, practical studies will be
carried out on sample datasets using the Weka application and students' ability
to solve certain data mining problems will be improved. During the semester,
students will do homework on the topics and will complete and present a term
project.
Students who successfully complete the course will gain the following
abilities:
(a) to understand data mining fundamentals, basic concepts, and
definitions,
(b) to understand the importance of data, acquisition, preprocessing,
and processing,
(c) to use Data Mining functions, models, and algorithms,
(d) to implement classification and regression functions,
(e) to realize clustering,
(f) to solve prediction problems,
(g) to use Weka Application.
Textbook – 1: Weka 3: Data Mining Software in Java

Link
Textbook – 2: Data Mining Concepts and Techniques, J. Han, M. Kamber, Morgan
Kaufmann Publishers, ISBN 13: 978-1-55860-901-3, ISBN 10: 1-55860-901-6.
Other: You can access many Data Mining books in our university library.
Dataset Links: 1) https://archive.ics.uci.edu/ml/index.php
2) https://www.cdc.gov/datastatistics/index.html
3) https://data.medicare.gov/data/hospital-compare#
4) http://data.imf.org/?sk=388DFA60-1D26-4ADE-B505-
A05A558D9A42&sId=1479329334655
5) Veri madenciliği problemleri ve veri setleri: https://www.kaggle.com/
6) https://www.paperswithcode.com/datasets
Dr. G. Çiğdem Çavdaroğlu – Fall 2021

COURSE SCHEDULE
Week Subject
Course Requirements, Schedule, and Introduction to Data Mining
Course Introduction. Requirements. Course Schedule. Introduction to Data Mining: Definition. History.
1
Requirements. Examples. Data Miner Concept. Knowledge - Science - Development Level. Technology's Force.
07.10.2021
Speed Concept. Difficulties and Obstacles in Data Mining. Related Technological Areas and Technology Value
Chain.
Data Mining Processes, Problem Recognition and Data Concept
2 What Data Mining Is Not. Basic Definitions: Data - Database - Data Warehouse. Data Mining Processes. Data
14.10.2021 Mining Problem Recognition. Examples with Sectoral Applications. Data Mining Functions: Identification –
Prediction.
Data Mining Functions and Models
3
Overview of Data Mining Functions. Descriptive Functions. Predictive Functions. How to Select the Best
21.10.2021
Function. Which Function / Model Is Better?
Descriptive Functions: Association Analysis and Association Rules
4 The Fundamental Logic of Descriptive Functions. Creating Association Rules. Data Acting Together. Market
28.10.2021 Basket Analysis. Terms Used in Creating Association Rules. Support and Trust Values. Methods Used in
Association Analysis (Algorithms). Apriori Algorithm Deep Look. Examples. Weka Practices.
Weka Application Installation and Practice
5 Weka Application Setup. Weka Screens. Information Flow in Weka: Execution of the Application. Arff File
04.11.2021 Upload. Target Limit Setting. Data Division. Access to Data Mining Functions. Access to Results and Evaluation
Screens. Presentation of Results.
Data Concept and Data Preprocessing
6
Purpose of Preprocessing. Why Data is Dirty. Importance of Data Preprocessing. Methods. Correction of
11.11.2021
Incorrect Data. Discrete Data Transformation. Missing Data Pre-Processing. Examples. Weka Applications.
Descriptive Functions: Sequential Analysis
7 Finding Sequential Patterns. Time Series Analysis. Space Series with Sequential Pattern in Time. Division Series.
18.11.2021 Compound Series. Sequential Analysis Methods (Algorithms). Deep Look at Algorithms. Examples. Weka
Applications.
Midterm Week
25.11.2021 Midterm: Covers the first 7 weeks’ subjects.
Descriptive Functions: Clustering
9 Obtaining Data with Similar Features from Data Set. Hierarchical Partitioning Methods. Density-Based
02.12.2021 Methods. Grid-Based Methods. Model-Based Methods. Methods Used for Clustering Function (Algorithms).
Deep Look at Algorithms. Examples. Weka Applications.
Predictive Functions: Regression Analysis
10 The Fundamental Logic of Predictive Functions. Regression (Curve Fitting). Recognizing Regression Problems.
09.12.2021 Methods (Algorithms) Used in Regression Analysis. Linear and Non-Linear Regression. Univariate and
Multivariate Regression. Deep Look at Algorithms. Examples. Weka Applications.
Determining the Model Quality in Supervised Methods
11
Making Quality Measurements of Models Produced by Different Methods. Quality Measurement Parameters.
16.12.2021
Why It Is Not Enough to Base on Accuracy Value in Some Methods? Examples. Weka Applications.
Predictive Functions: Classification
12 Classification (Categorization). Recognizing Classification Problems. Methods (Algorithms That Can Be Used
23.12.2021 for Classification). Bayes Classification. Nearest Neighbor Classification. Classification with Decision Trees.
Deep Look at Algorithms. Examples. Weka Applications.
Predictive Functions: Classification
13
Classification with Artificial Neural Networks. Classification with Support Vector Machines. Advanced Topics in
30.12.2021
Data Mining. Examples. Weka Applications.
Sample Applications with Weka
14 Solving Different Problems in Weka Environment. Determining the Main Subject of the Problem. Determining
06.01.2022 the Proper Data Mining Function. Selecting the Appropriate Method (Algorithm). Generating the Model.
Generating the Information. Solving the Problem. Presentation of the Problem Solution.
15 Term Project Presentations
13.01.2022 Review of the Semester. Presentation of Student Projects. Grading.

REQUIREMENTS:
1. This course is online. Students are obliged to attend the lessons as synchronously. The students who cannot
attend are obliged to watch the recordings.
2. Assignments will not be graded in this course. However, it is recommended to complete assignments in order
to understand the subject. Answers will be uploaded to the system. Students can compare their own work with
sample solutions uploaded to the system.
3. Students must complete and submit their project to pass the course. Projects that are not completed,
uploaded or submitted to the system on time will not be graded.
4. Students are responsible for the announcements made during the lesson, even on the days when they are not
in class.
GRADING POLICY: Grading will be based on the following ingredients:
Term Project % 10
Midterm % 35
Final Exam % 55
Total % 100
PASSING REQUIREMENTS: To pass the course, you must satisfy all the following: all other students will get a
failing grade (F) from this course.
• Students must have completed and presented the project on time

• Students must collect at least 40 points from the midterm to pass the course
• Students must collect at least 40 points from the final exam to pass the course
• Passing grade: 50 points
CHEATING AND PLAGIARISM POLICY:

In case of any form of copying and cheating on assignments or exams, all involved parties will get 0 from the
assignment/exam. Cheating has serious consequences such as suspension. Any assignment you submit (reports,
reviews etc.) must be your own work. Representing someone else's work as your own is plagiarism. It is a serious
offence to take credit for a paper that you did not write yourself. If you use someone else’s work in your
assignments without providing the citation you will get 0 from the assignment. The students who will perform
these actions will fail the course.

ITEC4433 - Data Warehousing and Data Mining

Uploaded by

Copyright:

Available Formats

ITEC4433 - Data Warehousing and Data Mining

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

ITEC4433 - Data Warehousing and Data Mining

Uploaded by

Copyright:

Available Formats

ITEC4433 - Data Warehousing and Data Mining

Semester: 2021 Fall

Textbook – 1: Weka 3: Data Mining Software in Java

Dr. G. Çiğdem Çavdaroğlu – Fall 2021

Dr. G. Çiğdem Çavdaroğlu – Fall 2021

GRADING POLICY: Grading will be based on the following ingredients:

• Students must have completed and presented the project on time

CHEATING AND PLAGIARISM POLICY:

Dr. G. Çiğdem Çavdaroğlu – Fall 2021

You might also like