All programmes > Data Science for Business

Data Science for Business (B-KUL-D0I74A)

6 ECTSEnglish52 First termCannot be taken as part of an examination contract
Verbeke Wouter (coordinator) |  Baesens Bart |  Verbeke Wouter
POC zij-instroom Masters FEB

Aims

Upon completion of this course, the student is able to:

  • Understand and explain what data science and analytics are.
  • Understand and explain how different types of data-driven methods can be used in business to support decision-making and create value.
  • Understand and explain the concepts of descriptive analytics (unsupervised learning), predictive analytics (supervised learning) and prescriptive analytics.
  • Understand and explain the analytics process model.
  • Understand and explain various data-driven methods, such as decision trees and ensemble methods, regression methods and neural networks, clustering methods, etc.
  • Acknowledge the importance of data and suggest and apply recent technologies to analyze data for developing effective data-driven business solutions.
  • Recognize and formulate different data-driven decision support solutions depending on decision problem characteristics.
  • Evaluate the quality of analytical models.
  • Implement, run and evaluate data analytical experiments using a specific toolset (for example, RapidMiner).
  • Evaluate and discuss the application of analytics in real life business settings.

Previous knowledge

  • At the beginning of this course, the student should be familiar with the fundamentals of information systems and their business applications, as taught in, for example, the course Business Information Systems (D0H27a).
  • Students should be familiar with basic statistical concepts, such as probability distributions and probability calculus.
  • Background knowledge of business economics is useful, but not strictly necessary.
  • Programming knowledge is not a requirement, but students are expected to have general skills in using computers and software applications such as MS Word and MS Excel.

Is included in these courses of study

Activities

6 ects. Data Science for Business (B-KUL-D0I74a)

6 ECTSEnglishFormat: Lecture52 First term
Baesens Bart |  Verbeke Wouter
POC zij-instroom Masters FEB

Content

Part 1: Data Science Foundations

  • Chapter 1: Introduction to Data Science
  • Chapter 2: Preprocessing
  • Chapter 3: Predictive Analytics - Decision Trees
  • Chapter 4: Postprocessing
  • Chapter 5: Predictive Analytics - Nearest Neighbors and Ensembles
  • Chapter 6: Predictive Analytics - Regression
  • Chapter 7: Predictive Analytics - Artificial Neural Networks
  • Chapter 8: Descriptive Analytics - Clustering, Association and Sequence analysis, Anomaly Detection
  • Chapter 9: Prescriptive Analytics - Uplift Modeling and Causal Machine Learning
  • Chapter 10: Prescriptive Analytics - Cost-sensitive Learning, Evaluation and Decision-making
  • Chapter 11: Prescriptive Analytics - Multi-armed Bandits and Reinforcement Learning

Part 2: Data Science Applications

  • Chapter 1: Credit Risk Modeling
  • Chapter 2 Fraud Analytics
  • Chapter 3: Customer Lifetime Value
  • Chapter 4: Recommender Systems
  • Chapter 5: Web Analytics
  • Chapter 6: Other applications (HR Analytics, Sentiment analysis, Supply Chain Analytics, Ethics and AI)

Course material

Course material

  • Course material will be made available on Toledo: slides, reader, etc.
  • Course material consists primarily of what has been taught during lectures

Recommended Reading

  • Foster Provost and Tom Fawcett, Data Science for Business: What You Need to Know about Data Mining and Data-Analytic Thinking, 1st edition, O'Reilly Media, ISBN-13: 978-1449361327
  • In addition, articles and papers will be provided on Toledo.

Toledo

  • Toledo is being used for this learning activity.

Language of instruction: more information

English

Format: more information

The focus of this course is on explaining the learning content. Students are expected to critically and thoroughly study the theory and examples that are presented during the lectures.
Assignments take place during the academic year. Cases, demonstrations, guest lectures are also included.

Evaluation

Evaluation: Data Science for Business (B-KUL-D2I74a)

Type : Partial or continuous assessment with (final) exam during the examination period
Description of evaluation : Written, Paper/Project
Type of questions : Multiple choice
Learning material : None

Explanation


Features of the evaluation

* Assignments take place during the academic year and count for 20% of the final mark. Assignments may have to be carried out in teams of multiple students. The deadline for submitting the assignments will be communicated via Toledo by the lecturer.
* The final exam takes place on-campus, consists of multiple choice questions covering both parts (Part I: Data Science Foundations and Part II: Data Science Applications) of the course equally, and counts for 80% of the final mark.

Determination of final grades

* The grades are determined by the lecturer as communicated via Toledo and stated in the examination schedule. The result is calculated and communicated as a number on a scale of 20.
* There is a correction for guessing on multiple choice questions, unless indicated otherwise.
* The final grade is a weighted score consisting of one or more assignments (20%) and the final examination (80%). The assignments take place during the academic year.

Second examination opportunity

* The retake exam may consist of open questions or multiple-choice questions, or a combination of both.
* Marks for assignments are counted again in the third exam period. Students can retake assignments upon request by e-mail to the lecturer by July 10 latest.