The construction industry plays a major role in the boost of the country’s economy, providing basic facilities for residential and creating thousands of job opportunities. During COVID-19, the construction sectors in Sindh Pakistan was highly suffered and leading to delays in the completion of projects. As the construction sector was globally affected, building construction projects were also affected by completing the projects on estimated time and cost. Thus, this research investigates the significant factors of time and cost that affected the Hyderabad building construction projects during COVID-19 situation. Questionnaire surveys were designed to collect data from the employees working on building projects in Sindh Pakistan. The collected data was analyzed through the Average Index method. Unsafe working environment; shortage of workers; and increasing project cost was observed as significant factors that were highly affected during COVID-19. The results and findings shall be supportive for stakeholders to take into consideration of factors in the early stage of the expected pandemic situation. This research suggested that the stakeholders shall modify or amend the contract clause regarding for pandemic situation and incorporate the identified factors in the contract that should be considered by stakeholders to save the time and cost of the projects.

Cost prediction for construction projects provides important information for project feasibility studies and design scheme selection. To improve the accuracy of early-stage cost estimation for construction projects, an improved neural network prediction model was proposed based on BP (back propagation) neural network and Snake Optimizer algorithm (SO). SO algorithm is adopted to optimize the initial weights and thresholds of the BP neural network. Cost data for 50 construction projects undertaken by Shandong Tianqi Real Estate Group in China was collected, and the data samples were clustered into three categories using cluster analysis. 18 engineering feature indicators were determined through a literature review and 10 feature indicators were selected using Boruta algorithm for the input set. Compared to BP neural network and PSO–BP neural network, the results show that the improved SO–BP model has higher prediction accuracy, stability, better generalization ability and applicability. Therefore, based on reasonable feature indicators, the method proposed in this paper has certain guiding significance for predicting engineering costs.