Extended Abstract
Introduction
In Iran, residential projects—especially in the peripheries of large cities—face significant challenges, including delays, cost overruns, poor quality, weak coordination among stakeholders, and multiple risks. The peri-urban areas of Shiraz, experiencing rapid construction growth and increasing pressure on housing supply, provide a suitable context to analyze how AI can be integrated into residential project management. Rapid population growth and housing demand highlight the need for professionally managed residential projects. Without leveraging modern technologies like AI, resources may be wasted, risks increase, and construction quality may decline. Examining AI applications in the peri-urban areas of Shiraz can identify successful patterns and local challenges, offering practical guidance to decision-makers and construction firms. Therefore, a case study in Shiraz’s peri-urban spaces can serve as a local reference model.
In Iran, residential projects—especially in the peripheries of large cities—face significant challenges, including delays, cost overruns, poor quality, weak coordination among stakeholders, and multiple risks. The peri-urban areas of Shiraz, experiencing rapid construction growth and increasing pressure on housing supply, provide a suitable context to analyze how AI can be integrated into residential project management. Rapid population growth and housing demand highlight the need for professionally managed residential projects. Without leveraging modern technologies like AI, resources may be wasted, risks increase, and construction quality may decline. Examining AI applications in the peri-urban areas of Shiraz can identify successful patterns and local challenges, offering practical guidance to decision-makers and construction firms. Therefore, a case study in Shiraz’s peri-urban spaces can serve as a local reference model.

Methodology
This study adopts a descriptive–analytical and applied research approach. Its main goal is to examine and analyze the impact of AI applications on residential project management in Shiraz’s peri-urban areas. Since the research seeks to uncover relationships between variables and measure the level of impact, quantitative statistical methods and field data analysis were employed. Data were collected using a researcher-made questionnaire covering two variables: “AI applications in residential projects” and “residential project management,” designed based on indicators extracted from previous domestic and international studies. The statistical population included experts, professionals in construction, and academic researchers related to project management and technology. Using a convenience sample (snowball sampling), the sample size was 209, and stratified random sampling ensured adequate representation of each group. The questionnaire’s validity was confirmed by expert opinions in project management and IT, and reliability was verified via Cronbach’s alpha (α = 0.93), indicating excellent reliability. Data were analyzed using SPSS version 26.

Results and discussion
The findings indicate that AI applications have a significant and substantial impact on improving peri-urban residential project management. Pearson correlation results showed a very strong and positive relationship between AI applications and project management (r = 0.971), meaning that increased use of AI tools in design, supervision, scheduling, and cost control directly enhances project management effectiveness. This underscores AI’s role as a key driver in improving efficiency, decision-making accuracy, and reducing managerial risks in peri-urban projects. Simple linear regression results show a determination coefficient of R² = 0.943, indicating that approximately 94% of the variation in residential project management can be explained by AI applications. The model’s statistical significance (Sig = 0.000) and high F-statistic (F = 1343.7) confirm its validity, demonstrating that the independent variable effectively predicts the dependent variable.
ANOVA results reveal significant differences among expert groups (construction sector, municipality, and academic/research institutions) regarding AI’s impact on residential project management (F = 157.946). This suggests that familiarity and interaction with AI technologies vary across work environments, with each group perceiving AI’s impact differently based on activity type and technology access. Duncan post-hoc tests indicated the highest mean scores for academics/researchers (4.69), experts (3.99), and construction practitioners (3.53). These results show that academics, due to greater familiarity with AI theories, algorithms, and functionalities, have the strongest belief in AI’s effectiveness, whereas construction practitioners, due to operational and infrastructure limitations, perceive lower impact. Overall, these differences emphasize the need for training programs, knowledge transfer, and technological investment in peri-urban project operations.


Conclusion
This study demonstrates that AI applications have a strong and positive effect on peri-urban residential project management. Increased use of intelligent technologies in design, supervision, scheduling, and cost control enhances project managers’ performance in terms of time, cost, and quality. The high determination coefficient confirms AI’s role as a strong explanatory factor in improving project management. Moreover, differences in perceptions among expert groups highlight the importance of training, knowledge transfer, and technological investment to effectively utilize AI in operational settings.

Keywords: Artificial Intelligence, Residential Project Management, Peri-Urban Areas, Shiraz