Construction Contract Price Prediction Model for Government Buildings Using a Deep Learning Technique: A Study from Thailand

Government building projects are particularly complex due to their scale and number of end users, which makes construction prices time-consuming and prone to error. Machine learning is recognized for its ability to process large volumes of complex data quickly with high accuracy, but only a limited number of studies have applied Deep Learning in the early construction stage. Therefore, we aimed to evaluate the potential of Deep Learning to predict construction contract prices for government buildings. Factors were identified through a literature review and interviews with eight experts, and data were collected from 300 government construction projects obtained from Thailand’s Electronic Government Procurement (e-GP) database, the national centralized platform for transparent public bidding. By varying the number of parameters, 80 models were developed and tested. The best-performing model had a three-hidden-layer ratio of 128:64:32 with a Quadratic Loss Function, achieving an R2 of 0.918 and an RMSE of 2.022. The results showed 14 significant factors, with the top 5 being (1) usable area, (2) number of sanitary wares, (3) number of rooms, (4) height, and (5) number of elevators. Sensitivity analysis was subsequently conducted to enhance the explainability of the model. The findings demonstrate the potential of Deep Learning to enhance the accuracy of determining construction price and support more effective government budget planning and decision making.