Assessing Residual Value of Heavy Construction Equipment Using Predictive Data Mining Model

Construction equipment constitutes a significant portion of investment in fixed assets by large contractors. To make the right decisions on equipment repair, rebuilding, disposal, or equipment fleet optimization to maximize the return of investment, the contractors need to predict the residual value of heavy construction equipment to an acceptable level of accuracy. Current practice of using rule-of-thumb or statistical regression methods cannot satisfactorily capture the dynamic relationship between the residual value of a piece of heavy equipment and its influencing factors, and such rules or models are difficult to integrate into a decision support system. This paper introduces a data mining based approach for estimating the residual value of heavy construction equipment using a predictive data mining model, and its potential benefits on the decision making of construction equipment management. Compared to the current practice of assessing equipment residual values, the proposed approach demonstrates advantages of ease of use, better interpretability, and adequate accuracy.

[1]  D. Heckerman,et al.  Autoregressive Tree Models for Time-Series Analysis , 2002, SDM.

[2]  Gunnar Lucko,et al.  Predicting the Residual Value of Heavy Construction Equipment , 2003 .

[3]  Gregory M. Perry,et al.  Durable Asset Depreciation: A Reconciliation between Hypotheses , 1990 .

[4]  Timothy L. Cross,et al.  Depreciation Patterns for Agricultural Machinery , 1995 .

[5]  Carl T. Haas,et al.  Automated quality assessment of stone aggregates based on laser imaging and a neural network , 2004 .

[6]  Jing Wu,et al.  Estimating Farm Equipment Depreciation: Which Functional Form is Best? , 2004 .

[7]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[8]  Patrick van der Smagt,et al.  Introduction to neural networks , 1995, The Lancet.

[9]  Simaan M. AbouRizk,et al.  Decision support in construction equipment management using a nonparametric outlier mining algorithm , 2008, Expert Syst. Appl..

[10]  Donald W. Reid,et al.  On Optimal Replacement of Farm Tractors , 1983 .

[11]  James R. Unterschultz,et al.  Reducing Investment Risk in Tractors and Combines with Improved Terminal Asset Value Forecasts , 1996 .

[12]  Christine M. Anderson-Cook,et al.  Unknown Element of Owning Costs — Impact of Residual Value , 2007 .

[13]  Edward I. George,et al.  Bayesian Treed Models , 2002, Machine Learning.

[14]  David Maxwell Chickering,et al.  Efficient determination of dynamic split points in a decision tree , 2001, Proceedings 2001 IEEE International Conference on Data Mining.

[15]  David Arditi,et al.  Predicting the Outcome of Construction Litigation Using Boosted Decision Trees , 2005 .

[16]  Gregory M. Perry,et al.  The Effect of Usage and Size on Tractor Depreciation , 1990 .

[17]  Alberto Maria Segre,et al.  Programs for Machine Learning , 1994 .

[18]  J. R. Quinlan.  Learning With Continuous Classes , 1992 .

[19]  Aram Karalic.  Linear Regression in Regression Tree Leaves , 1992 .

[20]  Padhraic Smyth,et al.  From Data Mining to Knowledge Discovery: An Overview , 1996, Advances in Knowledge Discovery and Data Mining.

[21]  Christine M. Anderson-Cook,et al.  Statistical Considerations for Predicting Residual Value of Heavy Equipment , 2006 .

[22]  Awad S. Hanna,et al.  Decision Tree Approach to Classify and Quantify Cumulative Impact of Change Orders on Productivity , 2004 .

[23]  Roger Mcneill.  Depreciation of Farm Tractors in British Columbia , 1979 .