DATA-DRIVEN OPTIMIZATION OF CONSTRUCTION PRODUCTIVITY IN COMMERCIAL BUILDINGS USING GENETIC ALGORITHM

This study focuses on the optimization of time, cost, and resource utilization in commercial building construction using a Genetic Algorithm approach. The increasing complexity of modern construction projects necessitates the adoption of advanced techniques beyond traditional scheduling methods. Conventional methods such as CPM and PERT are limited in handling multi-objective optimization problems involving conflicting project parameters. This research aims to develop an efficient optimization framework that integrates time, cost, and resource constraints. A detailed literature review was conducted to identify research gaps and establish the theoretical foundation of the study. A structured methodology was adopted, including data collection, problem formulation, and model development. Project data such as activity durations, costs, and resource requirements were analyzed to represent real construction scenarios. An optimization model was formulated with defined objective functions and constraints. A Genetic Algorithm was implemented using MATLAB to generate optimal and near-optimal solutions. The algorithm employed operations such as selection, crossover, and mutation to improve solution quality iteratively. The optimized results were compared with traditional scheduling methods to evaluate performance improvements. The findings demonstrate significant reductions in project duration and cost along with improved resource utilization. This study provides a practical and efficient approach for enhancing construction project management and supports decision-making in commercial building projects.