Decision Models

General characterization

Prerequisites

Students should have basic knowledge of Linear programming.

Bibliography

All content (theory and exercises are on the UC website at www.unidemi.com/models.

Additional content can be found in the following books:

1) Applied Management Science: Modeling, Spreadsheet Analysis, and Communication for Decision Making,2nd Edition, 

John A. Lawrence, Barry A. Pasternack, ISBN: 978-0-471-39190-6, February 2002

2) Management Decision Making: Spreadsheet Modeling, Analysis, and Application

George E. Monahan

ISBN 10: 0521781183  ISBN 13: 9780521781183

Publisher: Cambridge University Press, 2000

Teaching method

Teaching method:
·      Lectures;
·      Discussion of case studies with students;
·      Problem solving sessions;
·      Team work;
·      Presentation and discussion of team works;
·      Assessment.

Evaluation method

The final assessment of the curricular unit (UC) of Decision Models (MDc) will be based on the following elements:

- 1 Global Test (T), with 70% weight in the final assessment

- 1 Group Work (TG). It consists of the development of a work to be carried out as specified. Groups will have a maximum of 4 students.

The final MDc grade will be composed as follows:

Final grade = 0.70*T + 0.30*TG

Where:
T - test score;
TG - group work note

The score for each of the assessment components is rounded to the nearest tenth.

To be approved at the UC, students must obtain frequency at the UC through a positive grade (>=9.5 values) in the group work. Approval occurs if the Final Grade is equal to or greater than 9.5 values ​​in both evaluation elements.

If a student has not passed the global test, if he/she has attended the current year or the previous year, he/she may take the appeal exam. The final grade will be calculated by the same formula, replacing the test grade with the exam grade.

Subject matter

1. Fundamentals of Decision-Making
1.1. Decision-making process in Industrial Engineering
1.2. Framework of decision types in operations, logistics, and investments
1.3. Decision environments: Certainty, Risk, and Uncertainty
1.4. Types of models and applications in:
1.4.1. Business profitability analysis
1.4.2. Inventory management
1.4.3. Production planning and control
1.4.4. Investment project analysis
2. Deterministic Models – Linear Programming (LP)
2.1. Formulation and solution of LP models for industrial problems
2.2. Introduction to Solver as a decision-support tool
2.3. Basic structuring of problems: production mix, lot sizing/order sizing, make-or-buy decisions, investment evaluation, capacity allocation to clients
2.4. Applications in:
2.4.1. Lot sizing in production
2.4.2. Capacity planning
2.4.3. Production planning and sequencing
2.4.4. Inventory and transportation management
2.4.5. Make-or-buy decision
2.4.6. Investment evaluation
2.5. Sensitivity analysis with Solver in logistics and production problems
2.5.1. Incremental variations of coefficients and constraints
2.5.2. Shadow price and reduced cost
2.5.3. Interpretation in industrial context problems
3. Decision Analysis
3.1. Payoff matrices in industrial and business decisions
3.2. Non-probabilistic criteria:
3.2.1. Maximax
3.2.2. Maximin
3.2.3. Hurwicz criterion
3.2.4. Laplace criterion
3.2.5. Minimax regret
3.3. Probabilistic criteria and decision trees:
3.3.1. Structuring and evaluation of states and nodes
3.3.2. EMV – Expected Monetary Value
3.4. Value of information in industrial decisions:
3.4.1. EPPI and EVPI
3.4.2. Bayesian analysis and conditional probabilities
3.4.3. EVSI and efficiency of additional information
3.5. Types of additional information in the context of industrial and business decisions
3.6. Sensitivity analysis in decision trees
3.7. Utility theory:
3.7.1. Preference and risk analysis in Industrial Engineering
3.7.2. Modeling utility functions according to decision-maker’s risk profile
3.7.3. Certainty equivalent and risk profile
3.8. Applications in:
3.8.1. Single-period models (newsvendor problem) for seasonal inventory management
3.8.2. Facility and logistics center location
3.8.3. Capacity planning
3.8.4. Industrial investment evaluation
3.8.5. Coordination of promotional campaigns and strategic partnerships
4. Multi-Attribute Utility Theory (MAUT)
4.1. Types of objectives in industrial and business decisions
4.2. Modeling of utility functions (linear and exponential)
4.3. Aggregation method and final scoring
4.4. Applications in:
4.4.1. Technology selection
4.4.2. Procurement management and supplier qualification
5. Multicriteria Decision-Making
5.1. Analytic Hierarchy Process (AHP):
5.1.1. Hierarchical structure
5.1.2. Scales and pairwise comparison matrices
5.1.3. Priority calculation and consistency
5.1.4. Elicitation of decision-maker’s preferences and opinions
5.2. Technique for Order Preference by Similarity to Ideal Solution (TOPSIS)
5.3. Group decision-making
5.4. Applications in:
5.4.1. Supplier selection and qualification
5.4.2. Investment evaluation
5.4.3. Industrial facility and logistics unit location
5.4.4. Project management
6. Monte Carlo Simulation
6.1. Simulation process in spreadsheets
6.2. Random variables and statistical distributions
6.3. Risk analysis methods
6.4. Applications in:
6.4.1. Inventory management
6.4.2. Production planning and control
6.4.3. Capacity planning and resource allocation
6.4.4. Investment analysis based on time value of money
6.4.5. Maintenance management
7. Integrative Project in Industrial Engineering
7.1. Development of a practical case integrating different decision-support methodologies
7.2. Application to real problems in operations, logistics, production, or investments
7.3. Group work with presentation and discussion of results

Programs

Programs where the course is taught: