The performance of engineering activities has significant impacts on the successfulness of implementing industrial construction projects. Improving engineering performance can lead to better project outcomes. Previous studies on engineering performance improvement have either focused on the use of certain techniques or products, or looked at specific engineering processes or areas. There has been a lack of a systematic and analytical approach that improves engineering performance based on the understanding of the relationships between engineering inputs and project outcomes. The paper proposes a generic model, which integrates genetic algorithms with artificial neural networks, for modeling engineering performance measurement and improvement in industrial construction projects. Due to their robust and efficient search ability in complex situations, genetic algorithms are employed to search for solutions to improving engineering performance with the searching criteria, fitness function, being the neural networks that establish the relationships between engineering inputs and project outputs.