course-details-portlet

BBAN4005

Deep Learning and Explainable AI for Business Analytics

New from the academic year 2026/2027

Assessments and mandatory activities may be changed until September 20th.

Credits 7.5
Level Second degree level
Course start Spring 2027
Duration 1 semester
Language of instruction English
Location Trondheim
Examination arrangement Empirical project paper

About

About the course

Course content

This course introduces students to deep learning and explainable AI (xAI), and focuses on their practical application in a business context through an empirical project on a self-chosen topic in business. Depending on the student’s interests and specialization, this topic could involve finance, economics, marketing, customer behavior analytics, operations, organizational studies, fraud detection, credit default or bankruptcy prediction, electricity price prediction, asset pricing, or other business applications.

Introduction

Over the past decade, deep learning has driven an ongoing revolution in artificial intelligence (AI), transforming a wide range of fields. From early breakthroughs to today’s generative AI systems like ChatGPT, deep learning continues to push the boundaries of what AI can achieve.

As the use of AI and machine learning continues to grow, the importance of xAI has become increasingly evident. xAI plays a crucial role in ensuring that complex models remain transparent, interpretable, and accountable. This is particularly important in high-stakes domains such as finance, law, workplace decision-making, and other areas where AI systems directly affect individuals and society.

Course content

This course will cover the following topics:

  • Artificial neural networks and deep learning
  • Introduction to common deep learning architectures
  • Training deep artificial neural networks
  • Explainable artificial intelligence (xAI), including SHAP (SHapley Additive exPlanations)
  • Data handling and processing with Pandas and NumPy in Python
  • TensorFlow and Keras for deep learning

In addition, through a graded empirical project paper, students will learn how to apply deep learning and xAI within the context of the field of their master’s degree.

Learning outcome

Knowledge

By the end of this course, the student shall be able to:

  • Understand and describe how deep artificial neural networks function and how they are applied for data explanation and prediction.
  • Understand how deep artificial neural networks are trained.
  • Recognize common challenges in training deep artificial neural networks and how to mitigate them.
  • Understand how xAI approaches can help developers and users of machine learning models to enhance performance, justify predictions, and gain insights into model behavior.

Skills

By the end of this course, the student shall be able to:

  • Use Pandas and NumPy in Python to handle and process data.
  • Set up a coding environment with TensorFlow and Keras for deep learning.
  • Apply deep learning to solve problems within the field of their master’s degree.
  • Apply xAI methods to address problems relevant to the field of their master’s degree.
  • Design and customize a variety of deep learning architectures.
  • Implement appropriate procedures for training deep artificial neural networks.

General competence

By the end of this course, the student shall be able to communicate with both specialists and the general public about:

  • The strengths and limitations of using deep learning to solve problems within the field of their master’s degree.
  • How various xAI approaches can help developers and users of machine learning models to enhance performance, justify predictions, and gain insights into model behavior.

Learning methods and activities

Lectures, self-study, work on a project paper, and supervision by lecturer.

Compulsory assignments

  • Compulsory assignments

Further on evaluation

The course grade is based on an empirical project paper that students will complete in groups of two or three members and submit by the end of the semester. Working alone as a single-member group may be allowed, subject to approval by the course coordinator early in the semester. Collaborating with other students in a group of more than one student is highly recommended.

The project paper shall apply methods covered in this course to address one or more self-chosen problem statements within a topic related to the students’ field of their master’s degree. The topic and problem statement(s) may be something the students plan to explore further in their master’s thesis, or they may be unrelated.

The grading scale is A-F, where F indicates a fail.

To qualify for submitting the empirical project paper and receiving a grade in this course, students must first complete and pass the following compulsory assignments:

  • Submit a short project description early in the semester
  • Submit a preliminary draft of the project paper
  • Present their preliminary draft orally to the lecturer, followed by supervision to help improve the final project paper
  • Submit the presentation slides used in the oral presentation

Specific conditions

Admission to a programme of study is required:
Accounting and Auditing (MRR)
Economics (MSØK)
Economics (MSØK/5)
Economics and Business Administration (MSIVØK5)
Economics and Business Administration (ØAMSC)
Entrepreneurship (MENTRE)
Entrepreneurship (MSENTRE)
Financial Economics (MFINØK)
Industrial Economics and Technology Management (MTIØT)
International Business and Marketing (860MIB)
Management of Technology (ØAMLT)

Required previous knowledge

None.

Course materials

Course materials will be announced at the start of the semester.

Subject areas

  • Economics and Administration

Contact information

Course coordinator

Department with academic responsibility

NTNU Business School

Examination

Examination

Examination arrangement: Empirical project paper
Grade: Letter grades

Ordinary examination - Spring 2027

Empirical project paper
Weighting 100/100 Exam system Inspera Assessment