Improper management of labour resources causes major problems for companies working on multiple industrial construction projects. To address these problems, an integrated framework is developed based on a five-step knowledge discovery in data model. The framework transfers existing multidimensional historical data from completed projects into useful knowledge for future projects.

First, a synthesis of previous research is presented. Second, an inclusive analysis of the industrial construction domain is performed. Third, the concept of predefined progressable work packages is introduced to address issues in current data management practices. Fourth, a prototype data warehouse is built using the snowflake schema to centrally store the data, produce dynamic reports and exchange knowledge. Fifth, data mining techniques are applied to extract useful knowledge from three sets of real projects data.

Results show that the developed framework is capable of transferring previously unanalyzed data to valuable knowledge that significantly improves current resources management practices.