Conceptual cost estimates are often made at the beginning of the project when project scope is not yet well defined. Hence, predicting the conceptual costs on time, with high accuracy, presents a considerable challenge. One potential solution is to more effectively utilize historical data via integration with predictive analytical models. In this project, a decision support system was developed which predicts conceptual costs of construction projects and supports decision-making for long-term capital planning in public universities. The prototype system was developed based on historical data for roofing projects at the University of Alabama. We collected this historical data via a web-based data entry form subsystem. The developed system uses ridge regression models to train historical data. This system has a user-friendly interface and supports what-if analysis, allowing the user to see multiple scenarios of the estimation. The system also encompasses capabilities to forecast the effects of inflation on multi-year projects. Subsequent validation has demonstrated improvement in the resulting accuracy of the conceptual estimates.