Applied Information Economics (AIE)
Measure what Matters, Make better Decisions
A decision is only as good as the data and analysis on which it is based. Our proprietary quantitative analytical method, Applied Information Economics, provides a proven, scientific framework for measuring anything and using the results to make more informed – and better – decisions.
An Overview of Applied Information Economics
Applied Information Economics (AIE) is a synthesis of techniques from economics, actuarial science, and other mathematical methods (see Figure 1). AIE employs methods that are proven by a large body of peer-reviewed academic research and empirical evidence on improving human expert judgments.
Even though AIE was based on academic support and evidence, it is a practical approach that helps HDR clients every day in a variety of real industry, government, and humanitarian efforts. We have implemented AIE in to over 100 major decision portofolios.
Some of the basic techniques that make AIE a powerful set of tools include a method for clarifying decisions and defining variables in a quantitative way, calculation methods for the value of information, methods for modeling uncertainty as estimates, measurement methods, and treating the decision as a choice among different investment portfolios. These methods are part of a formalized procedure that includes the following major activities:
- Define the Decision(s): We help our clients identify the real decision at the outset. Is the dilemma whether to simply approve a project or how to conduct a project given a vast combination of alternatives? Or is the decision a matter of when a given initiative should be approved? The costs, benefits, timing, risks and even external factors are identified and the real decision is clarified
- Model What We Know Now: Cost estimates, market forecasts, project risks, and other variables in a typical big investment decision are almost never known exactly. Usually, the uncertainty about some variables, especially long term forecasts, can seem extreme. But even extremely uncertain variables can be assessed using HDR’s methods. AIE uses methods to compensate for the natural overconfidence and the inconsistency of most managers and decision makers. This results in measurably better forecasts and decisions. These methods are shown to work even when organizations have very little historical data, complex problems, and measurements that seem almost impossible.
- Measure What Matters: AIE’s unique approach to uncertain decisions involves picking the right things to measure. Not all variables in a decision are worth measuring and those worth measuring are often a surprise to the decision makers. In fact, most managers measure exactly the wrong things – that is, the most uncertain variables tend to be ignored while the variables that usually receive a lot of attention actually have less bearing on the decision. With AIE, every variable in a model will have an “information value” that allows identification of high value variables in a decision.
- Make Better Decisions: This can include decisions that are more than just “accept/reject” choices but possible combinations of several choices. The final outcomes must consider the risk preferences of decision makers. The output of the decision model, updated with economically justified measurements, is compared to the risk appetite of the organization.
The output of this process is not a point scale or “high, medium, low” rating. AIE produces results that would be familiar to actuaries and quantitative financial analysts. For ERM, portfolio risk is illustrated with what is known as a Loss Exceedance Curve (LEC). As Figure 2 illustrates, we would generate an initial or “inherent” risk curve and a subsequent “residual risk” curve after risk mitigations are employed.
Both curves are compared to a “risk tolerance” curve to determine if a proposed action imposes or mitigates risks to within a level deemed to be acceptable to management. The inherent risk curve (in red) shows that, prior to risk mitigation actions, there was a 45% chance of losing more than $10 million in each year and an 8% chance of losing more than $100 million. This is much more exposure to loss than management will accept, as shown by the risk tolerance curve (in black). After mitigating actions are taken, the residual risk curve (in green) is entirely below the risk tolerance curve.
By taking a mathematically sound approach, this allows us to compute a “Return on Control” (RoC) for each proposed risk mitigation. The spreadsheet will be able to show expected RoC for many mitigations at once so that control priorities can be determined.