Publication

Abstract : Prices of real estates in metropolitan landscapes harbour immense importance in steering the complexities of dynamic city environments. In India, the real estate sector contributes around 6–7% to India's GDP. Therefore, accurate forecasting of real estate prices is a factor in making informed decisions, affecting various stakeholders. Many techniques were used for this in past several years, like Hedonic models, Repeat-Sales models, Rule-Based Systems and Heuristics, etc. This study leverages the power of machine learning and big data to develop a robust framework for predicting housing prices in metropolitan landscapes. We employ PySpark, a powerful big data processing framework with built-in MLlib library (machine learning library), to analyse large-scale housing data encompassing various cities in India & to predict the prices for the same. By implementing a comparative analysis of prominent regression models - Random Forest, Linear Regression, Decision Tree, and Gradient-Boosted Tree - our approach identifies the most effective algorithms for real estate price prediction using MLlib library. Also, this study highlights the need for scalable solutions to manage an increasing number of data sources and emphasizes the PySpark library which will simplify big data handling and enable parallel computing. This study paves the way for utilizing advanced machine learning techniques and big data platforms to gain valuable insights into real estate markets. Our findings emphasize the critical role of combining these powerful tools to navigate the complex dynamics of urban housing and predict prices with greater accuracy.