Development of a Predictive Analytics-Driven Decision Support System for Smart Construction Schedule Control

Abstract

Schedule delays remain a recurring concern in Philippine vertical construction projects. In the projects examined, delays were associated with design revisions, vendor-related problems, procurement activities, site conditions, and external factors such as adverse weather. Conventional project monitoring methods are largely descriptive and provide limited support for anticipating schedule disruptions. This study developed a data-driven Decision Support System (DSS) that integrates schedule performance metrics, delay analysis, predictive modelling, and Microsoft Power BI visualization for construction schedule control. Historical data from selected residential, commercial, and mixed-use construction projects were analyzed using Pearson correlation and multiple regression to examine relationships among schedule performance, delay factors, and environmental conditions and to develop a delay prediction model. The DSS supports schedule monitoring through key performance indicators, including the Schedule Performance Index (SPI), and provides delay forecasts. Design revisions and vendor-related issues accounted for the largest shares of reported delay factors, while Gravity Level showed the strongest relationship with schedule delay. The regression model yielded an R² of 0.78 and an adjusted R² of 0.75, indicating that the selected predictors explained approximately 75% of the variation in delay duration. These findings support earlier identification and management of schedule risks.