||Forecasting construction industry-level total factor productivity growth using neural network modeling
||Mao Zhi, Goh Bee Hua, Wang Shouqing, Ofori G
||Total Factor Productivity (TFP) is widely recognised as a better indicator thanLabour Productivity and Multi-Factor Productivity to represent industry-levelproductivity performance. Productivity is the key determinant of a nation'sstandard of living and an industry's competitiveness. As such, the ability to predicttrends in TFP growth in the construction industry is very important. The factorsinfluencing TFP growth in the construction industry are complicatedly interrelated.This fact made the conventional regression method highly inadaptable to suchcomplex multi-attribute nonlinear mappings.As an AI information-processing tool, the artificial neural network (ANN) systemhas been proven to be a powerful approach to solving complex nonlinear mappingswith higher accuracy than regression methods. However, so far, there has beenlittle application of ANNs in predicting TFP growth in the construction field. Thisstudy will for the first time, apply the concepts of ANNs to develop a model toforecast the TFP growth in the case of the construction industry of Singapore.Macro-level information processing models are useful in monitoring and predictingthe performance of the construction industry as a whole. With the need to manageconstruction performance information at all three levels, namely, industry, firm andsite, this study looks specifically at developing an 'intelligent' model for forecastingindustry-level productivity.Meanwhile, using the same set of data, a model developed by the Multiple LinearRegression method will serve as a benchmark to judge the performance of the ANNmodel. The ANN model, compared with the traditional regression model, would beexpected to have better forecasting ability for TFP growth in the constructionindustry, in terms of accuracy.
|Year of publication:
Mao Zhi, Goh Bee Hua, Wang Shouqing, Ofori G (2002).
Forecasting construction industry-level total factor productivity growth using neural network modeling. Agger K (ed.); Distributing knowledge in building; Arhus, June 12 - 14, Denmark (ISSN: 2706-6568),