Abstract—Equipment owner have realized that professionalized equipment management offers cost advantages. The procurement strategy as one of the most important tasks for equipment managers changed from simply buying heavy equipment to make use of different options regarding leases and sales. Nevertheless, a strategic and cost efficient heavy equipment procurement is only one import step towards a strategic equipment management. As a next step there is need to improve the utilization of heavy equipment regarding equipment logistics, maintenance and repair to increase return on investment over the equipment’s lifecycle. Therefore, the paper presents an approach to predict a reliable heavy equipment demand by computing the monthly utilization rate with support vector machines regression. In total, sample data of over 111 construction projects between 2013 and 2015 is computed. A better knowledge of the upcoming equipment demand for future projects allows to progress from an ad-hoc equipment management to a data-driven strategic equipment management. Benefits of the presented approach are discussed in order to increase return of investment by renting out unused equipment or in order to balance out the heavy equipment fleet by reducing respectively buying new equipment.

Index Terms—heavy equipment management, support vector machine regression, prediction models

Cite: A. Kargul, A. Glaese, S. Kessler, and W. A. Günthner, "Heavy Equipment Demand Prediction with Support Vector Machine Regression Towards a Strategic Equipment Management," International Journal of Structural and Civil Engineering Research, Vol. 6, No. 2, pp. 137-143, May 2017. doi: 10.18178/ijscer.6.2.137-143