Predicting project and activity duration for buildings in the UK

This paper reports on the development of a computer model that will predict both overall project and activity duration, based on a number of pre-determined project characteristics. Fifty-six programmes of work were obtained. The data from the programmes of work of fifty of these buildings, encompassing a total of 11 different project types, were analysed, and used to develop the proposed model. Multiple linear regression analysis of the data showed that the duration and time lags of between 20 (for a single storey building) and 39 (for a seven-storey building) standardised activity groups, can be predicted using combinations of the twenty one most influential project variables. The regression equations produced were tested on all of the activity groups for six new projects to determine their accuracy. The absolute percentage error in predicting overall duration varied between 0.38% and 6.68%. The mean absolute error in predicting the duration of activity groups varied between 1.38% and 22%. The accuracy in predicting overall duration was comparable with limited information available from previous studies, but the high level of detail in the programme generated means that the model is more flexible and capable of a broader range of applications than previous models. © World Scientific Publishing Company.