Universal Prediction Model for Construction Litigation

Abstract

Construction litigation expenditures have increased considerably over the years. An universal prediction model (UPM) was developed to predict the outcome of construction litigation and, hence, encourage settlements out of court. The study was conducted by using 151 Illinois circuit court cases filed in the period 1987–2005. UPM consists of data consolidation, attribute selection, hybrid classification, and performance assessment. A code was written to automate the entire process in the Waikato environment for knowledge analysis. UPM is versatile and scalable. The findings resulted in a higher prediction rate than those obtained in previous studies. The system proved to be quite robust and fast. If the outcome of construction litigation can be predicted with reasonable accuracy and reliability, all parties involved in the construction process could save considerable money and time.