Data-Driven Intelligent Model for Sale Price Prediction and Monitoring of a Building

Abstract

The construction cost forecasting and monitoring plays an important role in a building condition assessment. The construction cost of a building (CCB) not only depends on the method of construction, equipment, labor, and material but also depends on type, scheduling, project locality, and project duration, etc. Moreover, abrupt variations in economic indices and attributes (i.e., WPI: wholesale price, liquidity, building services, etc.) are reasons for cost variation and deviate the CCB, which are not possible to monitor and/or identify in easy way during the current economic scenario. So, these indices may be snubbed in CCB. In this chapter, a data-driven intelligent model for sale price monitoring and detection of a building is presented which may be utilized in hospital planning. For the implementation of the proposed approach, the cost's data of construction for 372 buildings of three to nine stories have been utilized. The recorded dataset has physical, financial, and economic variables and indices of real sites. The proposed approach includes the comparative analysis of conventional statistical and advanced soft computing techniques. The obtained results show that monitor and/or identification of CCB is higher in case of soft computing technique than statistical method.