English   Danish

2022/2023  KAN-CCMVI2085U  Machine Learning for Predictive Analytics in Business

English Title
Machine Learning for Predictive Analytics in Business

Course information
Language English
Course ECTS 7.5 ECTS
Type Elective
Level Full Degree Master
Duration Summer
Start time of the course Summer
Timetable Course schedule will be posted at calendar.cbs.dk
Max. participants 60
Study board
Study Board for MSc in Economics and Business Administration
Course coordinator
  • Raghava Rao Mukkamala - Department of Digitalisation
For academic questions related to the course, please contact course responsible Raghava Rao Mukkamala (rrm.digi@cbs.dk).
Main academic disciplines
  • Finance
  • Information technology
  • Economics
Teaching methods
  • Face-to-face teaching
Last updated on 16-11-2022

Relevant links
Learning objectives
By the end of this course students will be able to:
  • Have a good understanding of the fundamental issues and challenges of machine learning
  • Appropriately choose and appraise machine learning algorithms for predictive analytics in business
  • Effectively use Python to process, summarize and visualize business data
  • Effectively use Python to develop machine learning algorithms to solve business problems
Course prerequisites
Completed Bachelor degree or equivalent. Fundamental mathematics and statistics will be reviewed in the course. However, students are expected to have received some mathematics and/or statistics training in their undergraduate studies, e.g., calculus, linear algebra and probability theory. No programming skills and experience are needed. Students will learn Python programming from scratch in this course.
Examination
Machine Learning for Predictive Analytics in Business:
Exam ECTS 7,5
Examination form Home assignment - written product
Individual or group exam Individual exam
Size of written product Max. 15 pages
Assignment type Written assignment
Duration Written product to be submitted on specified date and time.
Grading scale 7-point grading scale
Examiner(s) One internal examiner
Exam period Summer
Make-up exam/re-exam
Same examination form as the ordinary exam
First re-take: 72-hour home assignment, max. 10 pages.
If the number of registered candidates for the make-up examination/re-take examination warrants that it may most appropriately be held as an oral examination, the programme office will inform the students that the make-up examination/re-take examination will be held as an oral examination instead.


Exam form for 3rd attempt (2nd retake): The second retake is always an online oral exam (20 minutes online oral exam with no preparation time) with one internal examiner and an internal co-examiner.
Course content, structure and pedagogical approach

Machine learning has been widely applied to support business in a range of areas, such as fraud detection, sales forecasting, inventory pricing, and consumer segmentation. This course introduces machine learning to students in business subjects. There will be a strong emphasis on predictive analytics, to enable students to frame and solve business problems using data-driven machine learning algorithms. It is self-contained, covers both theory and practice. Fundamental mathematics and statistics will be reviewed, and students will learn Python programming from scratch in this course. Each class is combined with lecture (theory) and workshop (practice). Students need to have their computers with Internet access. 

   

Preliminary assignment: A couple of questions related to business mathematics and statistics

Class 1: Introduction and review of mathematics and statistics

Class 2: Basic Python syntax, data I/O and handling

Class 3: Data visualization in Python

Class 4: Linear models for regression  

Class 5: Logistic regression

Class 6: Artificial neural networks

Midway mock exam

Class 7: K-nearest neighbors and naive Bayes 

Class 8: Tree-based models

Class 9: Support-vector machines 

Class 10: Cluster analysis

Class 11: Course review and Q&A for the exam
Description of the teaching methods
The teaching methods will be face-to-face teaching in class (students need to bring their laptops as we will perform analytics practice).
Feedback during the teaching period
Student survey feedback.
Mock exam solutions.
Student workload
Preliminary assignment 20 hours
Classroom attendance 33 hours
Preparation 126 hours
Feedback activity 7 hours
Examination 20 hours
Further Information
Ordinary 6 weeks course.
 
Preliminary Assignment: The course coordinator uploads Preliminary Assignment on Canvas at the end of May. It is expected that students participate as it will be included in the final exam, but the assignment is without independent assessment&grading.
 

Course and exam timetable is/will be available on https://www.cbs.dk/en/study/international-summer-university/courses-and-exams

 

We reserve the right to cancel the course if we do not get enough applications. This will be communicated on https://www.cbs.dk/en/study/international-summer-university/courses-and-exams in start March.
Expected literature

Mandatory readings:

  • Kevin Murphy. Machine Learning: A Probabilistic Perspective, MIT Press 2012. (Chapters 1-3, 7, 8, 14, 16)
  • Christopher Bishop. Pattern Recognition and Machine Learning, Springer 2007. (Chapters 5, 9)
  • Wes McKinney. Python for Data Analysis: Data Wrangling with Pandas, NumPy, and IPython, O'Reilly, 2012. (Chapters 4, 5)

Additional relevant readings:

  • Marc Deisenroth, Aldo Faisal, and Cheng Soon Ong. Mathematics for Machine Learning, Cambridge University Press, 2020. (Chapters 2, 4-6)
Last updated on 16-11-2022