Interactive explainer

Robust decisions – interactive calculator

How much should you order when demand is uncertain? The same numbers produce different quantities under different decision rules. This calculator makes explicit which uncertainty and which kind of loss each rule addresses.

Compare three decision rules for the same order. A unit costs €6 and sells for €10. Possible demand is 20, 40 or 60 units. You can change the probability of high demand and the salvage value of unsold stock. Selecting a criterion highlights its preferred quantity. All results are calculated locally in your browser.

Interactive

Robust decisions – interactive calculator

With €2 salvage value and a 40% probability of high demand, expected value and minimax regret select 40 units, while maximin selects 20.

Three experiments

  1. Change the rule. Compare expected value, maximin and minimax regret without changing any other input. Check the worst payoff and maximum regret for each quantity in the table. Different answers here come from different objectives, even though the underlying outcomes are identical.
  2. Make high demand more likely. Increase its probability substantially. The remaining probability is divided equally between low and medium demand. Observe why only the expected values react to this change.
  3. Reduce the cost of overordering. Increase salvage value and compare all three rules again. The payoff matrix now changes, so the robust choices may change as well. Reset the example afterwards.

Limits of this comparison

Maximin and minimax regret protect only against the three included demand states. Additional delivery problems, fixed costs and demand outside those values are absent. Regret measures a missed opportunity compared with perfect advance knowledge; it does not necessarily mean a negative payoff. Ties favour the smaller order. The robust decisions article explains the full calculation and how to choose an appropriate criterion.

From NyxAI

smartlytics is the learning hub of NyxAI GmbH.

Explore the methods we work with, explained openly, with sources and calculations you can reproduce.

Decision Core

NyxAI is developing a Decision Core for Decision Intelligence that combines optimisation, simulation, statistics and reinforcement learning: compare options, make uncertainty visible and learn from outcomes, with people in control.

AI workflows at NyxAI

DeepSquare

Explainable chess AI with human playing styles: NyxAI’s testing ground for understandable decisions under time pressure.