اميرمحمد جلوخاني نياركي

The primary objective of this study is to develop a model for predicting the average housing prices across the 22 districts of Tehran, taking into account the key indicators influencing the housing market. To achieve this goal, nine major indicators with significant impact on housing prices were identified through a review of related literature and expert consultation in the real estate domain. Subsequently, relevant data on these indicators, along with monthly housing price records for each district from October 2017 to June 2024, were collected through library resources and field studies, amounting to approximately 30,000 data entries. A crucial part of this research involved selecting an appropriate model for forecasting housing prices. After eva‎luating conventional approaches and reviewing prior studies, machine learning algorithms were adopted as the most suitable method. The final model demonstrated a high level of accuracy in predicting average housing prices over time and across different districts of Tehran. The findings of this research can be beneficial for various stakeholders, including real estate investors, developers for optimizing budget planning, and government agencies for formulating future housing policies. By analyzing the relationship between housing prices and influential indicators such as population and urban regulations, the proposed model provides valuable insights for macro-level policy planning. A notable contribution of this study is the application of advanced machine learning techniques to forecast average housing prices in Tehran. Unlike previous studies that have mostly focused on hedonic indicators or individual property comparisons, this research emphasizes region-specific indices and the comprehensive analysis of Tehran's 22 municipal districts.

شاخص‌هاي كليدي‌ , قيمت مسكن , مدلسازي سرمايه‌گذاري , شهر تهران

Key Indicators , Housing Prices , Investment Modeling , Housing Market , Tehran City

Amir Mohammad Jelokhani Niaraki

Dr. Yaser Sobhani Fard