Empirical Risk Assessment of Maintenance Costs under Full-service Contracts

Abstract

We provide a risk assessment, including data pre-processing, exploration and statistical modeling, on a portfolio of about 5 000 full-service maintenance contracts of industrial equipment. These contracts cover all maintenance related costs during a predetermined horizon in exchange for a fixed, upfront fee. Inspired by insurance pricing, we show how a data-driven analysis based on contract and machine characteristics, or risk factors, supports a differentiated, risk-based break-even tariff plan. Charging each contract a price proportional to its risk prevents adverse selection by incentivizing low risk (i.e., maintenance-light) profiles to not renege on their contracts. We employ generalized additive models (GAMs) to predict the risk factors' impact on the frequency (number of) and severity (cost) of maintenance interventions. GAMs are interpretable, yet flexible statistical models that capture the effect of both continuous and categorical risk factors. Our predictive models are capable to differentiate the contract cost estimation based on the contract and machine type, service history and machine running hours. We additionally utilize the predictive cost distributions of our models to augment the break-even price with the appropriate risk margins to further protect against the inherent stochastic nature of the maintenance costs.