Decision Sciences
Decision Sciences is the study of quantitative and qualitative techniques used to understand and improve decision-making by analyzing data, modeling uncertainty, optimizing outcomes, and incorporating human behavior and strategic thinking.
Elements of Decision Sciences
| Element | What it Involves |
|---|---|
| Descriptive | Understanding how decisions are actually made (often using behavioral and cognitive science). |
| Prescriptive | Recommending optimal decisions using models, optimization, and simulations. |
| Predictive | Using data and statistical/machine learning models to forecast outcomes. |
| Normative | Defining how decisions should be made under rationality and utility theories. |
Types of Decisions
1. By Structure
| Type | Description | Examples |
|---|---|---|
| Structured Decisions | Routine, repetitive, rule-based; can be automated | Inventory reordering, payroll processing |
| Unstructured Decisions | Complex, novel, no clear procedure; high uncertainty | Entering a new market, product innovation |
| Semi-Structured Decisions | Combination of both; partial rules but also human judgment needed | Loan approvals, hiring decisions |
2. By Scope
| Type | Description | Examples |
|---|---|---|
| Strategic Decisions | Long-term, high-impact, often unstructured | Mergers, business model selection |
| Tactical Decisions | Medium-term, implement strategic goals | Marketing campaigns, resource allocation |
| Operational Decisions | Day-to-day, often structured, support tactical decisions | Inventory restocking, scheduling |
3. By Method of Analysis
| Type | Description | Examples |
|---|---|---|
| Descriptive Decisions | Focus on understanding actual behavior and processes | Why consumers choose brand A over B |
| Normative Decisions | Ideal decisions based on logic, probability, and utility theory | Maximizing expected return |
| Prescriptive Decisions | Provide actionable recommendations based on models | Portfolio optimization, route planning |
4. By Environment
| Type | Description | Examples |
|---|---|---|
| Decisions under Certainty | All outcomes and probabilities are known | Choosing the cheaper of two known prices |
| Decisions under Risk | Probabilities of outcomes are known | Investing in stock with known volatility |
| Decisions under Uncertainty | Outcomes and probabilities are unknown or hard to estimate | Entering a new market without historical data |
5. By Participants
| Type | Description | Examples |
|---|---|---|
| Individual Decisions | Made by a single decision-maker | Choosing a job offer |
| Group Decisions | Made collectively by a team or group | Boardroom decisions, committee voting |
| Organizational Decisions | Made at different levels of an organization | Company restructuring, policy design |
Structured Study Plan for Decision Sciences
1. Foundations of Decision Sciences
Key Topics:
- What is Decision Sciences?
- Types of decisions (structured, unstructured, semi-structured)
- Normative vs. descriptive decision models
Readings:
- “An Introduction to Management Science” by Anderson, Sweeney, Williams (for OR + decision making)
- “The Decision Book” by Mikael Krogerus & Roman Tschäppeler (simple models)
- ISO/IEC 13273-1: Vocabulary on Decision-making Concepts (optional)
2. Decision Theory & Models
Key Topics:
- Expected utility theory
- Decision trees
- Bayesian decision theory
- Risk attitudes and utility functions
Readings:
- “Smart Choices: A Practical Guide to Making Better Decisions” by Hammond, Keeney, and Raiffa
- “Decisions with Multiple Objectives” by Keeney and Raiffa
- “Decision Analysis for Management Judgment” by Goodwin & Wright
- “Thinking, Fast and Slow” by Daniel Kahneman (for behavioral insights)
3. Mathematical & Statistical Tools
Key Topics:
- Probability & statistics
- Linear algebra
- Optimization basics (linear, nonlinear)
- Simulation modeling
Readings:
- “Introduction to Probability” by Bertsekas & Tsitsiklis
- “Statistics for Business and Economics” by Newbold, Carlson, Thorne
- “Operations Research: Applications and Algorithms” by Winston
- “Simulation Modeling and Analysis” by Averill M. Law
4. Optimization & Operations Research
Key Topics:
- Linear programming, integer programming
- Network models, transportation problems
- Multi-objective optimization
- Metaheuristics (genetic algorithms, simulated annealing)
Readings:
- “Introduction to Operations Research” by Hillier & Lieberman
- “Convex Optimization” by Boyd & Vandenberghe (more advanced)
- INFORMS resources and journals (e.g., Interfaces, Management Science)
5. Behavioral Decision Science
Key Topics:
- Bounded rationality
- Heuristics and biases
- Prospect theory
- Group decision-making
Readings:
- “Judgment in Managerial Decision Making” by Max Bazerman & Don Moore
- “Predictably Irrational” by Dan Ariely
- “Thinking, Fast and Slow” by Kahneman (again—core material here)
- “Nudge” by Thaler & Sunstein
6. Data-Driven Decision Making
Key Topics:
- Descriptive, predictive, and prescriptive analytics
- Data visualization
- Business intelligence
- Decision support systems (DSS)
Readings:
- “Data Science for Business” by Foster Provost and Tom Fawcett
- “Business Intelligence: A Managerial Perspective on Analytics” by Sharda, Delen, Turban
- “Competing on Analytics” by Thomas H. Davenport
- “Python for Data Analysis” by Wes McKinney (for practical data work)
7. Simulation and Systems Thinking
Key Topics:
- Monte Carlo simulation
- Systems modeling
- Feedback loops in decision processes
- Dynamic decision environments
Readings:
- “The Fifth Discipline” by Peter Senge (systems thinking)
- “Thinking in Systems” by Donella Meadows
- “Business Dynamics: Systems Thinking and Modeling” by John D. Sterman
- “Simulation with Arena” by Kelton, Sadowski, and Zupick
8. Advanced & Specialized Topics (Optional)
- Multi-Criteria Decision Analysis (MCDA)
- Game Theory
- Decision-making with AI and ML
- Behavioral game theory
Readings:
- “Multi-Criteria Decision Analysis: Methods and Software” by Ishizaka & Nemery
- “Game Theory: An Introduction” by Steven Tadelis
- “Reinforcement Learning: An Introduction” by Sutton & Barto (AI decision-making)
- “Behavioral Game Theory” by Colin Camerer
Tools and Platforms to Learn
| Tool | Purpose |
|---|---|
| Python (pandas, NumPy, scikit-learn) | Data analysis, optimization models |
| R (caret, tidyverse) | Statistical modeling |
| Excel Solver | Basic decision modeling and LP |
| Gurobi / CPLEX | Advanced optimization |
| Power BI / Tableau | Data visualization for decisions |
| AnyLogic / Arena | Simulation modeling |
Suggested Study Timeline (Approximate)
| Phase | Duration | Focus |
|---|---|---|
| Phase 1: Foundations | 2–3 weeks | Decision types, models, and basic logic |
| Phase 2: Math & Stats Core | 3–4 weeks | Probabilities, statistics, optimization |
| Phase 3: Decision Models | 3–4 weeks | Trees, utilities, Bayesian reasoning |
| Phase 4: Tools & Data | 4–6 weeks | Python, data analytics, DSS |
| Phase 5: Behavioral & Systems | 4–5 weeks | Human decision factors, systems thinking |
| Phase 6: Capstone / Project | 2–4 weeks | Solve a real decision problem end-to-end |