Study Guide

Learning outcomes

The student can:

- describe the steps of the data analytics process and understand the role of data analytics in modern business
- combine information sources of different content and different forms into usable data matrices
- use tools in gathering, describing, and visualizing various types of information
- produce and interpret key statistical measures and figures
- construct a simple predictive model using machine learning methods and evaluate its quality

Implementation and methods of teaching

The course has online lectures and self-study material. Students will do assignments and an online exam related to the topics of the course.

Timing and attendance

12.9.- 17.11.2024. Online lectures Thu 12.9.2024, Fri 20.9.2024, Thu 26.9.2024, Thu 3.10.2024, Thu 17.10.2024. Online exam Thu 31.10.2024. Final assignment deadline Sun 17.11.2024. Attendance is not mandatory but preferable. No personal assignments or guidance due to missing lectures

Learning material and recommended literature

Lecture and self-study material. Other materials indicated by the teacher.

Alternative completion methods

The course is completed only according to the presented model

Working life cooperation

It is possible to complete the course assignment, for example, at your own workplace or in your own company.

Exam retakes

Exam after the last lectures. Two re-examinations at separately announced times. Assignment must be completed.

Learning environment

Studying takes place online. Course material, information, return of assignments and exam in Moodle. Lectures will be recorded.

Student time use and work load

The course is 5 cr = 135 hours.

Lectures 20h
Independent study 30h
Assignment 58h
Exam preparation 25h
Exam 2h

Contents

Intro
Introduction to the topic, job descriptions, process flow, tools
Preparation
Data preparations and acquisition, feature selection, cleaning
Descriptive data analytics
Descriptive analytics methods, visualization techniques, distribution theory, hypothesis testing
Modeling
Basics of modeling, prediction and classification, k-fold cross-validation, model estimation

Assessment criteria

Exercise pass/fail
Exam

Assessment scale

1-5

Failed (0)

A rejected grade is given when the student has not achieved the learning objectives of the course. The student does not understand the aspects of data analytics and is not able to show any learning outcomes related to the topic in the exam and assignments.

Assessment criteria: level 1 (assessment scale 1–5)

The student is able to formulate a data analytics problem into an actionable plan
The student is able to extract data and perform reasonable feature selection
The student is able to produce visualizations related to the data analytics problem

Assessment criteria: level 3 (assessment scale 1–5)

Additionally:
The student is able to formulate a data analytics problem into an actionable plan and execute it
The student is able to extract data and perform reasonable feature selection and perform successful data cleaning and combination
The student is able to produce visualizations related to the data analytics problem and accompany them with simple testing
The student is able to construct a model for the data

Assessment criteria: level 5 (assessment scale 1–5)

Additionally:
The student is able to formulate a data analytics problem into an actionable plan and execute it
The student is able to extract data and perform reasonable feature selection and perform successful data cleaning and combination
The student is able to produce visualizations related to the data analytics problem and accompany them with simple testing
The student is able to construct a model for the data, test it, and evaluate its goodness