engleski

Critical variables for predicting cost of prefabricated housing

The paper analyzes application of neural networks together and factor analysis on cost prediction of prefabricated housing. The model relies on 7 critical variables, with following performances: 92, 85% of predicted values had the deviation lower 5% and 3, 57% had the deviation lower than 10%, in relation to actual values. The model was verified on 28 and validated on 3 buidings, with the deviation of 4.6% against actual values. With this model construction companies can, yet during tendering phase, effectively predict total cost of prefabricated housing and thus acquire competitive advantage in the market. However, for the model’s further validation, it is necessary to train the model on larger number of projects.

neural networks; factor analysis; Eigen value; building cost; prefabricated housing

nije evidentirano