نوع مقاله : مقاله پژوهشی
نویسندگان
1 گروه جغرافیا و برنامه ریزی شهری، دانشکده علوم انسانی، دانشگاه تربیت مدرس، تهران، ایران.
2 گروه جغرافیا و برنامه ریزی روستایی، دانشکده علوم انسانی، دانشگاه تربیت مدرس، تهران، ایران.
چکیده
کلیدواژهها
موضوعات
عنوان مقاله [English]
نویسندگان [English]
In a dynamic real estate market, accurate residential rent prediction is important for landlords, tenants, investors, and policymakers. This study aimed to develop an effective model for predicting residential rents in Tehran using supervised machine learning algorithms. The study used a dataset of 9,891 rental properties across Tehran’s 22 districts, with 17 property-related features recorded for each observation. The algorithms were evaluated using accuracy and precision metrics. The results showed that XGBoost achieved the best predictive performance, with both accuracy and precision reaching 98.1%. The decision tree model also performed well, achieving an accuracy of 96.3% and a precision of 96.1%. The strong performance of these tree-based algorithms may be related to their ability to identify complex and nonlinear relationships in the data. The findings can help real estate professionals, investors, and policymakers make better-informed decisions and improve rental pricing and housing strategies in Tehran. Future studies could improve the predictive performance of these models by adding further variables, such as neighborhood characteristics, spatial factors, and economic indicators. The models could also be tested in other cities and regions to assess their wider use and improve understanding of rental market patterns.
کلیدواژهها [English]
)