PRESCRIPTIVE ANALYTICS

This course provides students with solid methodological and quantitative modeling skills that are essential for analyzing economic and business systems and for supporting managerial decision-making.

The course Prescriptive Analytics examines quantitative methods and tools for formalizing decision problems and evaluating alternative courses of action in managerial settings, with particular attention to operational and strategic decisions in international contexts, such as global supply chains, capacity planning, budgeting, resource allocation, networks, and project management.

By the end of the course, students will have developed the knowledge and skills required to formulate, analyze, and assess decision problems through prescriptive models, in order to support managerial decisions in a rigorous and informed way across operational and strategic contexts.
1. Knowledge and understanding
• the role of prescriptive analytics within the descriptive–predictive–prescriptive chain and in managerial decision-making processes;
• the main optimization models, with particular reference to linear, integer, mixed-integer, and network models;
• the fundamental concepts of sensitivity and scenario analysis from a managerial perspective;
• the main assumptions, limitations, and risks of prescriptive models, with reference to data quality, uncertainty, robustness, fairness, and organizational constraints.
2. Applying knowledge and understanding
• formulate a decision problem by identifying decision variables, objectives, performance indicators, and operational and organizational constraints;
• implement and solve prescriptive models using software tools such as spreadsheets with Solver and/or Python environments;
• develop scenario analysis and what-if analysis to support decision-making;
• interpret model outputs, identify infeasibilities, trade-offs, and bottlenecks, and translate the results into operational and managerial recommendations.
3. Making judgements
• critically assess model quality and the consistency between data, assumptions, and proposed decisions;
• compare alternative modeling approaches, such as heuristics versus optimal solutions, deterministic versus scenario-based models, and single-objective versus multi-objective models, and justify their choices in a reasoned way;
• discuss the economic, organizational, and ethical implications and risks associated with the adoption of decision-support systems.
4. Learning skills
• critically consult textbooks, technical documentation, and online resources in order to extend models and techniques to new decision-making contexts;
• independently deepen their knowledge of prescriptive analytics methods and tools in response to evolving managerial problems and technological developments;
• document a prescriptive analysis in a rigorous and professional way, clearly presenting datasets, model structure, assumptions, results, and limitations.

Students are expected to have a basic background in math and in statistics, introductory knowledge of data analysis, and familiarity with the topics dealt with in the BUSINESS PROCESS ANALYTICS and ARTIFICIAL INTELLIGENCE FOR MANAGEMENT AND ORGANIZATIONS courses.
.
The course is taught in English.

To provide concrete solutions to today’s business challenges, the course adopts a rigorously data-driven and action-oriented approach.
Through its thematic modules, the program aims to equip participants with the essential decision-making tools needed to optimize resource management and navigate the complexities of the global supply chain.
Furthermore, to reinforce learning, each module combines theoretical content with the analysis of one or more practical case studies.

1. Prescriptive analytics and the decision cycle
The role of prescriptive analytics in managerial decision-making processes; definition of KPIs, costs associated with decision errors, constraints, and trade-offs; moving from data to decision.
2. Optimization modeling
Formulation of decision problems through decision variables, constraints, and objective functions; attention to consistency in units of measurement, managerial interpretation of the model, and model validation.
3. Linear programming, network models, and applications
Introduction to the main linear programming models and network models, with applications to managerial problems such as resource allocation, transportation, distribution, and planning.
4. Integer and mixed-integer programming
Analysis of decision problems involving discrete variables, with particular reference to assignment, knapsack, and facility location models; introduction to modeling issues and the main solution approaches at a conceptual level.
5. Uncertainty and robustness in decision-making
Analysis of the role of uncertainty in prescriptive models; introduction to scenario-based approaches and robust optimization; use of simulation and stress testing as decision-support tools.
6. Integration with predictive analytics and AI
Use of forecasts and machine learning models as inputs for prescriptive models; assessment of reliability, drift, and operational limitations; discussion of governance, transparency, and accountability issues in decision-support systems.

Course materials and reference readings, including research articles, institutional reports, datasets, and notebooks or worksheets, will be indicated by the instructor and made available through the Moodle platform.

Student assessment is organized in two stages: ongoing assessment and final assessment.
Throughout the course, students are encouraged to monitor and self-assess their learning through exercises and tests made available on the e-learning platform.
Final assessment is based on a written exam aimed at verifying the acquisition of analytical, problem-solving, and decision-support skills.
The exam requires students to formulate and/or analyze, and, where appropriate, solve one or more quantitative models related to typical business planning and management problems.

More specifically, students may be asked to:
• state and discuss the assumptions underlying the proposed models;
• explain the role, purpose, and limitations of a model as a simplified representation of a real-world context;
• interpret and discuss the results obtained, including their effectiveness and decision-making relevance.

Problems similar to those included in the final exam will be made available on the university e-learning platform.

Where the written exam does not allow a sufficiently clear assessment of:
• command of the technical language of the discipline;
• understanding of the fundamental concepts;
• the degree of autonomy and awareness shown in reasoning, justification, and connection of the acquired knowledge;
an additional oral exam may be required. This oral component serves as a complementary assessment tool in order to:
• clarify any ambiguities emerging from the written exam;
• directly verify conceptual understanding, use of specialist terminology, and critical reasoning skills;
• ensure a fair, consistent, and comprehensive evaluation of the competences actually acquired.

written and oral

The instructor is responsible for ensuring the authenticity and originality of all examinations and coursework. In cases of suspected academic misconduct, an additional on-site assessment may be required during the exams, which may differ from the standard format.

Final grading criteria
A. Marks in the 18–22 range will be awarded where students demonstrate:
• sufficient knowledge and understanding of the course contents, with reference to the main models and tools of prescriptive analytics;
• sufficient ability to formulate and apply decision and optimization models to basic managerial problems;
• limited ability to interpret model results and to formulate independent judgments regarding the proposed decisions;
• sufficient communication skills, especially in the use of the technical language of quantitative analysis and decision models.
B. Marks in the 23–26 range will be awarded where students demonstrate:
• fair knowledge and understanding of the course contents, with reference to prescriptive modeling methods and decision-support tools;
• fair ability to formulate, implement, and apply optimization models to managerial problems, including in the presence of operational and organizational constraints;
• fair ability to interpret results, analyze trade-offs, and formulate independent judgments in a coherent and reasoned way;
• fair communication skills, especially in the appropriate use of disciplinary technical terminology.
C. Marks in the 27–30 range will be awarded where students demonstrate:
• good or excellent knowledge and understanding of the course contents, with full command of the main methodological approaches in prescriptive analytics;
• good or excellent ability to formulate, implement, and apply prescriptive models to complex managerial analysis and decision problems;
• good or excellent ability to critically interpret results, discuss model assumptions, limitations, and robustness, and formulate well-grounded independent judgments;
• fully appropriate communication skills, with rigorous and confident use of the technical language of the discipline.

The course is primarily delivered through lectures and is further supported by teaching materials and learning modules made available on the university’s Moodle e-learning platform.

These modules guide students through the analysis and solution of case studies based on real-world managerial decision problems, enabling them to compare their own individual or group solutions with those discussed by the instructor and with approaches adopted in business and professional practice.

1) Students should register for the course on the dedicated page (Prescriptive Analytics) of the university e-learning platform moodle.unive.it

2) Accessibility, Disability and Inclusion
Accommodation and support services for students with disabilities and students with specific learning impairments

Ca’ Foscari abides by Italian Law (Law 17/1999; Law 170/2010) regarding support services and accommodation available to students with disabilities. This includes students with mobility, visual, hearing and other disabilities (Law 17/1999), and specific learning impairments (Law 170/2010). If you have a disability or impairment that requires accommodations (i.e., alternate testing, readers, note takers or interpreters) please contact the Disability and Accessibility Offices in Student Services: disabilita@unive.it.

This subject deals with topics related to the macro-area "Circular economy, innovation, work" and contributes to the achievement of one or more goals of U. N. Agenda for Sustainable Development