Decision Analysis with Artificial Intelligence Support (MOD500)

Immerse yourself in the intricacies of decision modeling and uncertainty analysis, exploring its vast applications. Built on the solid foundation of normative decision theory, this course combines prescriptive tools with state-of-the-art computational techniques, including AI. By harnessing the power of modern software and AI platforms like ChatGPT, stakeholders can adeptly navigate complex and uncertain decision terrains, culminating in insightful actions.

Course description for study year 2024-2025


Course code




Credits (ECTS)


Semester tution start


Number of semesters


Exam semester


Language of instruction



- Introduction: Embarking on decision insights and the pivotal role of data and AI.

- Uncertainty Modeling: Utilizing data analytics and AI tools to encapsulate the nuances of uncertain outcomes.

- Decision Theory: Theoretical underpinnings of informed decision-making.

- Basic Decision Analysis: Integrate Probabilistic Modeling and AI in Sensitivity Analysis, Value of Information Analysis, Risk Profiles, and Stochastic Dominance Analysis.

- Decision Modeling using Influence Diagrams: Structuring decision processes visually with AI enhancements.

- Modeling Risk Preferences: Understanding Risk Aversion, Risk Attitudes, and Utility Functions.

- Assessment of Probability Distributions: Leveraging data analytics and AI for deeper insights into potential outcomes' probabilities.

- The Decision Analysis Cycle/Process: A systematic approach to structured decision-making.

- Multiple Objective Decision Making: How to juggle and prioritize contrasting objectives.

- Options Thinking & Valuation in Decision Analysis: Infusing AI capabilities for advanced strategic foresight and valuation.

- ChatGPT in Decision Insights: Hands-on exploration of how ChatGPT can augment decision modeling and analysis. Join us on this transformative journey where traditional decision modeling meets the revolutionizing power of AI, ensuring a future of unparalleled clarity and informed actions.

Learning outcome


  • An understanding of modeling's role in strategic decision-making and of what constitutes a good decision model
  • A thorough understanding of essential elements of good modeling principles to strive for clarity in complex and uncertain decision-making situations.
  • Be able to recognize and account for the human biases and errors that most often affect decision making.
  • Develop models, tools, and mental frameworks that will allow you to deal effectively with uncertainty
  • Revise your beliefs after gathering additional information using Bayesian methods
  • Examine and quantify the value created by gathering additional information
  • Quantify your appetite for risk and how to factor this into your decision making
  • Use Bayesian Networks to help structure a decision model
  • Design models with a parametric approach to maximize insights
  • Anticipate decision-makers' questions and design in features to answer them
  • Build a decision model for a typical engineering or corporate decision situation
  • Discover how to create flexible models that allow you to analyze multiple strategic alternatives
  • Understand sensitivity analysis and the information it provides
  • Conduct probabilistic analysis to general additional insights and understand risk
  • Identify how to effectively communicate the insights derived from your model


  • Skills needed to build a good basic decision model and to use it in generating powerful insights into the decision situation
  • Be able to apply and construct decision models and to use the most important elements in decision analysis relevant to engineering type decision-making in the face of uncertainty.

General qualifications:

Students should understand fundamental logical principles and analyses and be able to communicate their choices and recommendations clearly.

Required prerequisite knowledge


Recommended prerequisites

A bachelor degree in engineering or equivalent


Written project report and written exam

Form of assessment Weight Duration Marks Aid
Report 1/2 1 Semesters Letter grades
Written school exam 1/2 4 Hours Letter grades All 1)

1) All aids allowed. Collaboration is not allowed.

Exam information for this course will be listed shortly.

Course teacher(s)

Course coordinator:

Reidar Brumer Bratvold

Course teacher:

Enrico Riccardi

Head of Department:

Alejandro Escalona Varela

Method of work

The work will consist of 6 hours of lecture and scheduled tutorials per week. Students are expected to spend an additional 6-8 hours a week on self-study, assignments, and project. Excel, Python, DPL and ChatGPT (and equivalents) will be used for assignments, projects and tests. The course does provide a short introduction to Python but it is NOT a course in Python so the students will need to consult other resources for learning Python if they are not already familiar with it. A brief introduction to DPL will also be provided early in the course

Open for

Single Course Admission to PhD-courses
Admission to Single Courses at the Faculty of Science and Technology
Exchange programme at Faculty of Science and Technology

Course assessment

There must be an early dialogue between the course supervisor, the student union representative and the students. The purpose is feedback from the students for changes and adjustments in the course for the current semester.In addition, a digital subject evaluation must be carried out at least every three years. Its purpose is to gather the students experiences with the course.


Search for literature in Leganto