Unit BUSINESS ANALYTICS
- Course
- Engineering management
- Study-unit Code
- A005333
- Curriculum
- In all curricula
- Teacher
- Andrea Genovese
- Teachers
-
- Andrea Genovese
- Hours
- 48 ore - Andrea Genovese
- CFU
- 6
- Course Regulation
- Coorte 2025
- Offered
- 2026/27
- Learning activities
- Caratterizzante
- Area
- Ingegneria gestionale
- Sector
- ING-IND/35
- Type of study-unit
- Obbligatorio (Required)
- Type of learning activities
- Attività formativa monodisciplinare
- Language of instruction
- English
- Contents
- The module offers a Decision Analytics perspective applied to Engineering Management, focusing on decision support in contexts characterized by multiple objectives, uncertainty, and conflicting interests.
The course introduces the fundamentals of organizational decision making, theories of bounded rationality, and problem structuring techniques (Value-Focused Thinking). Concepts of trade-off, dominance, Pareto efficiency, and the Pareto frontier are addressed, with an introduction to multi-objective models (weighted sum, Goal Programming).
The central part is dedicated to Multi-Criteria Decision Making (MCDM) methods: AHP, TOPSIS, PROMETHEE, and ELECTRE. For each method, assumptions, advantages, and limitations are discussed, with applications to supplier selection, technology assessment, supply chain design, and sustainability.
A specific section addresses decisions under uncertainty, introducing sensitivity analysis, scenario analysis, and Monte Carlo simulation. In the final part, students apply the methods studied to real problems in procurement, supply chain management, sustainability, and the circular economy. - Reference texts
- Main reference texts:
Goodwin, P. & Wright, G. (2014). Decision Analysis for Management Judgment. Wiley. (recommended supplementary reading for the decision making and cognitive biases part)
Wang, Z. & Rangaiah, G.P. (2026). Multi-Criteria Decision-Making: Principles, Methods and Programs. CRC Press.
Additional readings will be selected from the international scientific literature, with particular reference to the contributions of Herbert Simon, Bernard Roy, Thomas Saaty.
Additional teaching materials (slides, case studies, exercises, datasets, Python scripts) will be provided by the lecturer during the course and made available on the University e-learning platform. - Educational objectives
- By the end of the course, students will be able to:
1. Structure complex decision problems by identifying stakeholders, objectives, criteria, and alternatives, applying the principles of Value-Focused Thinking.
2. Apply the main Multi-Criteria Decision Making methods (AHP, TOPSIS, PROMETHEE) to evaluate and rank alternatives in the presence of conflicting criteria.
3. Assess the robustness of decisions through sensitivity analysis and scenario analysis.
4. Critically select the most appropriate analytical tools and communicate managerial recommendations based on quantitative analyses. - Prerequisites
- Basic skills in linear algebra, descriptive statistics, and elementary probability.
Knowledge of the fundamentals of Operations Research, including the ability to recognize and formulate a linear optimization problem.
Familiarity with programming languages (at a basic level). - Teaching methods
- The module consists of lectures and guided tutorials for a total of 48 contact hours. Lectures combine theoretical explanations, case discussions, and applied examples, supported by PowerPoint presentations, blackboard work, and the use of software applications.
Tutorials focus on solving quantitative problems, analysing real case studies, and practical workshops.
From a software perspective, the course mainly uses:
Excel for basic MCDM applications;
Python (Jupyter Notebook) for simulation, visualization, and sensitivity analysis activities (with pre-prepared scripts);
Decision Radar (web tool) for quick exercises on TOPSIS, ELECTRE, and other MCDM methods.
All teaching materials, including slides, exercises, datasets, Python scripts, and supplementary readings, will be made available through the University's virtual learning environment. - Other information
- Attendance: Attendance is not mandatory but is strongly recommended, given the progressive and cumulative nature of the content and the importance of workshop activities.
Office Hours: The lecturer is available to students for consultation. Office hours will be communicated at the beginning of the course and published on the lecturer's webpage. - Learning verification modality
- 1. Final Written Examination (50% of final grade): A 2-hour written exam consisting of open-ended questions aimed at verifying understanding of theoretical concepts and the ability to critically select the most appropriate tools to support a complex decision.
2. Individual Coursework (50% of final grade): Individual application of an MCDM method to a managerial problem assigned by the lecturer. The assignment includes problem structuring, application of the chosen method, analysis of results, and a critical reflection on the limitations of the approach adopted. An oral examination is performed, starting from the presentation of the project results. - Extended program
- The module will be articulated according to the following tentative structure.
Week 1: Introduction to decision-making processes in organizations. Management Science and Decision Support Systems. Herbert Simon and bounded rationality. Structuring decision problems: identifying stakeholders, objectives, and criteria. Introduction to Value-Focused Thinking.
Week 2: Trade-offs between conflicting objectives. Dominance, Pareto efficiency, and the Pareto frontier. Introduction to multi-objective models: weighted sum formulation. Goal Programming: basic formulation and applications.
Week 3: Overview of Multi-Criteria Decision Making (MCDM) methods. Classification of methods: compensatory and non-compensatory approaches. Introduction to the Analytic Hierarchy Process (AHP). Hierarchy construction, pairwise judgments, and weight calculation. Consistency checking.
Week 4: AHP tutorial with Excel. Application to a supplier selection or technology assessment case. Discussion of results and sensitivity analysis on weights. Guided exercise with software tools.
Week 5: The TOPSIS method (Technique for Order Preference by Similarity to Ideal Solution). Assumptions, algorithm, and interpretation of results. Advantages and limitations compared to AHP. TOPSIS tutorial with Excel and dedicated software.
Week 6: Outranking methods: PROMETHEE and ELECTRE. Theoretical assumptions and methodological differences. Preference flows, graphs, and outranking indices. When to use PROMETHEE vs. ELECTRE. Criteria for selecting the appropriate MCDM method.
Week 7: PROMETHEE tutorial. Application to a supply chain design or sustainability evaluation case. Discussion of results and sensitivity analysis.
Week 8: Decisions under uncertainty. Risk vs. uncertainty. Sensitivity analysis. Scenario analysis. Introduction to Monte Carlo simulation for assessing decision robustness.
Week 9: Tutorial on sensitivity and scenario analysis. Use of Python (Jupyter Notebook) with pre-configured scripts to visualize the impact of uncertainty on MCDM results. Basic Monte Carlo simulation.
Weeks 10 and 11: Integrated applications to management problems. Strategic procurement: supplier selection with multiple criteria. Supply chain design: evaluation of alternative configurations. Sustainability and circular economy: assessment of green initiatives. Discussion of real cases. - Obiettivi Agenda 2030 per lo sviluppo sostenibile
- The course contributes to the achievement of the following Agenda 2030 Goals:
Goal 4 (Quality Education): by providing advanced methodological skills for structuring and solving complex decision problems;
Goal 9 (Industry, Innovation, and Infrastructure): by developing skills for evaluating investments in innovative technologies and infrastructure through MCDM methods;
Goal 12 (Responsible Consumption and Production): by applying the methods studied to sustainability, circular economy, and responsible supply chain problems.