Abstract—Estimating costs of construction projects more accurately at the project development stage is crucial for feasibility studies and it is a key factor for their success. Construction costs are often underestimated and recent statistical studies show that errors in cost estimation have not diminished. This paper focuses on the development of a more accurate estimation technique for construction highway projects using Artificial Neural Networks. Different architectures of the network with 10, 15, and 20 neurons were trained and tested with the backpropagation algorithm. Based on this, data from fourteen highway projects in Brazil were collected and analyzed. Eleven parameters that contribute the most to the construction final budget were found after trials and errors. For the best scenario, an average cost estimation accuracy of 99% was achieved. This preliminary study showed the feasibility of the tool applied to projects in Brazil and may be used by public agencies in the future.