Monetary pricing of software development risks: A method and empirical illustration

The ability to price (monetize) software development risks can benefit various aspects of software development decision-making. This paper presents a risk pricing method that estimates two parameters for every individual risk factor: extra cost incurred per unit exposure, and project sensitivity, to that factor. Since variability is a widely used measure of risk in finance and decision sciences, the method derives risk pricing parameters by relating variability in risk factors to variability in project cost. This approach rests on the fact that a parametric cost estimator predicts project cost by adjusting the "nominal" cost of a project based on the expected values of risk factors (cost drivers), but the actual project cost often deviates from prediction because the actual values of risk factors normally deviate from expectations. In addition, to illustrate the viability of the method, the paper applies the method empirically with COCOMO data, to approximate risk pricing parameters for four risk factors (Personnel Capability, Process Maturity, Technology Platform, and Application Task). Importantly, though, the method could work equally well with data recorded based on other parametric cost estimators. The paper also discusses several areas that can benefit from benchmark risk pricing parameters of the kind we obtain.