MØLBA3002 Machine Learning

    • Number of credits
      7,5
    • Teaching semester
      2025 Spring
    • Language of instruction
      English
    • Campus
      Lillehammer
    • Required prerequisite knowledge

      Prerequisites: LDBA200 Applied programming. Recommended prerequisites: MØLBA3001 Data Engineering.

Course content

This course provides a foundation in supervised machine learning. It introduces regression and classification algorithms and teaches their use coupled with loss functions for optimal decision making. The topics covered are: 

  • Optimal decisions based on minimization of expected loss
  • Regression methods (linear regression, neural networks, etc.) 
  • Classification methods (logistic regression, discriminant analysis, naive Bayes classifier, etc.) 
  • Performance evaluation 
  • Bias-variance tradeoff
  • Model selection and averaging  
  • Regularization 
  • Cross validation and the bootstrap  

Learning Outcome

 

Knowledge

Upon completion of the course, the candidate shall:  

  • Have advanced knowledge of the main principles and methods used in machine learning (k1) 
  • Explain context-dependent possibilities and limitations of machine learning methods (k2) 
  • Discuss the main differences between regular data and "big data" in machine learning applications (k3) 
  • Have in-depth knowledge of machine learning’s role in business analytics (k4) 
  • Interpret and discuss recent research results comparing performance of various machine learning techniques applied to business or economic data (k5) 
Skills

Upon completion of the course, the candidate shall be able to: 

  • Apply and implement known machine learning algorithms for solving business problems (f1) 
  • Design selected types of algorithms and implement them (f2) 
  • Identify bottlenecks and propose changes to machine learning algorithms to improve performance (f3) 
  • Evaluate the expected performance of machine learning methods (f4) 
  • Make qualified choices of machine learning methods for a given business problem (f5) 
General competence

Upon completion of the course, the candidate shall be able to: 

  • Apply machine learning algorithms to gain new insight into a company's economic and managerial challenges (g1) 
  • Convey knowledge about the use of machine learning methods and communicate with experts on design and implementation of machine learning algorithms and applications (g2) 
Teaching and working methods

Teaching methods 

  • Lectures 
  • Problem solving sessions 
Required coursework
  • Mandatory homework assignments must be handed in before each teaching module (a total of 4). These will be combinations of practical and theoretical exercises covering key topics in the course.  
  • Three out of four homework assignments must be passed to be allowed to take the exam.  
  • Attendance on at least 50% of the course's lectures.
Form of assessment
  • 48-hour individual take-home exam (counts 40% of the grade). The exam consists of practical assignments and a written report. 
  • 4-hour individual school exam under attendance (counts 60% of the grade).     

Graded A-F, where E is minimum for passing the exam. Both exams must be passed for the student to pass the course.

Assessments
Form of assessmentGrading scaleGroupingDuration of assessmentSupport materialsProportionComment
Home exam
ECTS - A-F
Individual
48 Hour(s)
  • All
40 %
Written examination with invigilation
ECTS - A-F
Individual
4 Hour(s)
  • No support materials
60 %

Reading list

Faculty
Inland School of Business and Social Sciences
Department
Department of Business Administration