Foundational Concepts in Decision Making
📌 Decision making involves a set of concepts, principles, tools, or techniques to handle complex decision problems under specific conditions.
👥 The five core components of any decision-making problem are the Decision Maker, Alternative Courses of Action (controllable aspects), Nature or State of Nature (uncontrollable environment/scenarios), Consequences (quantifiable outcomes), and the resulting Payoff Matrix.
📊 Decision problems can be classified as single-shot, multiple-stage (sequential), discrete theory problems, or continuous problems, depending on repetition and limits.

Decision Making Under Certainty
🎯 Decision making under certainty assumes perfect information; the decision-maker possesses complete and accurate knowledge of all possible outcomes for every course of action.
💡 A case example involved a university decision on developing a Super App: comparing in-house development vs. outsourcing, where the goal was to minimize cost.
📉 In the example, in-house development was chosen as the optimal choice, resulting in a total cost of 5,000 units compared to the outsourced option's higher cost, based solely on cost minimization under certainty.

Decision Making Under Risk
🎲 Decision making under risk occurs when information is imperfect, meaning the decision-maker does not have complete certainty but knows the possible outcomes and can assign probabilities to them.
💰 The key concept here is calculating the Expected Monetary Value (EMV) for each alternative, calculated as the sum of (Outcome Value $\times$ Probability of that outcome).
📈 The optimal decision under risk is selecting the alternative that yields the maximum EMV (or minimum expected cost, depending on the objective).

Expected Value of Perfect Information (EVPI)
✨ EVPI measures the potential increase in EMV gained by obtaining complete, perfect information before making a decision.
💵 The formula is $EVPI = (\text{Maximum EMV with perfect information}) - (\text{Maximum EMV under risk})$.
✅ A decision-maker should acquire additional information only if the cost of acquiring that information (e.g., research cost) is less than the calculated EVPI.

Key Points & Insights
➡️ Decision theory models simplify real-world complexity by using assumptions like perfect information to structure problems, even if this perfection is rare in reality.
➡️ The primary difference between certainty and risk is the assignment of probabilities to the states of nature; in certainty, probabilities are effectively 1.0 for the known outcome, while in risk, they are probabilities between 0 and 1.
➡️ Decision makers must rigorously quantify consequences (cost, profit, revenue) to populate the Payoff Matrix and facilitate mathematical selection of the rational choice.

📸 Video summarized with SummaryTube.com on Dec 16, 2025, 04:39 UTC