Dynamic, Data-Driven Decision-Support Approach for Construction Equipment Acquisition and Disposal

Abstract

Successful acquisition and disposal of construction equipment—a capital-intensive business process—requires both experience and expertise, particularly when assessing fair market values of equipment. Although advanced predictive models capable of assessing equipment residual market value have been developed, these models cannot be automatically updated with new market data, rendering them less and less accurate over time. This study proposes a Bayesian inference–based method capable of integrating historical and dynamic data to more dependably predict the likelihood of acquiring equipment at bargain values (i.e., lower than market). This method is intended to better inform practitioners of ideal times, locations, and makes/models of equipment to purchase or sell. Historical data of a commonly used piece of construction equipment, the CAT 320 Excavator, were used to demonstrate the feasibility and validity of the proposed approach, which was found capable of generating dependable, representative results.