The intense nature of the competition in the construction industry is commonly acknowledged by professionals and researchers. Moreover, the owners commonly select the contractors based on how low they offer their bid prices and outbid their rivals. Gaining competitive advantage in order to win a contract is largely based on considering all cost components very carefully and systematically in estimating the bid price. A typical bid price consists of three main cost components, which include: direct costs (e.g., materials, equipment, laborers, etc.), indirect costs (e.g., salaries of the engineers and technical personnel, security, etc.), and bid mark-up (i.e., general overhead, profit and contingency). In the literature, various tools and techniques have been proposed for estimating bid mark-up size in construction projects. This study compares the prediction performances of the artificial neural network (ANN) and multiple regression analysis techniques (MRA). For this purpose, 52 factors that may affect the size of bid mark-up were identified and actual data of 80 public construction projects were obtained from 27 Turkish contractors in public projects in Turkey. The ANN and MRA based models were developed via MATLAB Neural Net Fitting and SPSS software programs, respectively and their prediction performances were evaluated using several statistical measures. (C) 2016 The Authors. Published by Elsevier Ltd.