Empirical risk assessment of maintenance costs under full-service contracts

in European Journal of Operational Research (in press)

We provide a data-driven framework to conduct a risk assessment, including data pre-processing, exploration, and statistical modeling, on a portfolio of full-service maintenance contracts. These contracts ... [more ▼]

We provide a data-driven framework to conduct a risk assessment, including data pre-processing, exploration, and statistical modeling, on a portfolio of full-service maintenance contracts. These contracts cover all maintenance-related costs for a fixed, upfront fee during a predetermined horizon. 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 agreements. We borrow techniques from non-life insurance pricing and tailor them to the setting of maintenance contracts to assess the risk and estimate the expected maintenance costs under a full-service contract. We apply the framework on a portfolio of about 5 000 full-service contracts of industrial equipment and show how a data-driven analysis based on contract and machine characteristics, or risk factors, supports a differentiated, risk-based break-even tariff plan. 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 quantify the impact of the contract and machine type, service history, and machine running hours on the contract cost. 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 inherently stochastic nature of the maintenance costs. The framework shows how maintenance intervention data can set up a differentiated tariff plan. [less ▲]

A dynamic “predict, then optimize” preventive maintenance approach using operational intervention data

in European Journal of Operational Research (2022)

We investigate whether historical machine failures and maintenance records may be used to derive future machine failure estimates and, in turn, prescribe advancements of scheduled preventive maintenance ... [more ▼]

We investigate whether historical machine failures and maintenance records may be used to derive future machine failure estimates and, in turn, prescribe advancements of scheduled preventive maintenance interventions. We model the problem using a sequential predict, then optimize approach. In our prescriptive optimization model, we use a finite horizon Markov decision process with a variable order Markov chain, in which the chain length varies depending on the time since the last preventive maintenance action was performed. The model therefore captures the dependency of a machine’s failures on both recent failures as well as preventive maintenance actions, via our prediction model. We validate our model using an original equipment manufacturer data set and obtain policies that prescribe when to deviate from the planned periodic maintenance schedule. To improve our predictions for machine failure behavior with limited to no past data, we pool our data set over different machine classes by means of a Poisson generalized linear model. We find that our policies can supplement and improve on those currently applied by 5%, on average. [less ▲]

Forecasting spare part demand using service maintenance information

in International Journal of Production Economics (2019), 213

We focus on the inventory management of critical spare parts that are used for service maintenance. These parts are commonly characterised by a large variety, an intermittent demand pattern and oftentimes ... [more ▼]

We focus on the inventory management of critical spare parts that are used for service maintenance. These parts are commonly characterised by a large variety, an intermittent demand pattern and oftentimes a high shortage cost. Specialized service parts models focus on improving the availability of parts whilst limiting the investment in inventories. We develop a method to forecast the demand of these spare parts by linking it to the service maintenance policy. The demand of these parts originates from the maintenance activities that require their use, and is thus related to the number of machines in the field that make use of this part (known as the active installed base), in combination with the part's failure behaviour and the maintenance plan. We use this information to predict future demand. By tracking the active installed base and estimating the part failure behaviour, we provide a forecast of the distribution of the future spare parts demand during the upcoming lead time. This forecast is in turn used to manage inventories using a base-stock policy. Through a simulation experiment, we show that our method has the potential to improve the inventory-service trade-off, i.e., it can achieve a certain cycle service level with lower inventory levels compared to the traditional forecasting techniques for intermittent spare part demand. The magnitude of the improvement increases for spare parts that have a large installed base and for parts with longer replenishment lead times. [less ▲]