International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 04 | Apr 2024
p-ISSN: 2395-0072
www.irjet.net
HOUSE PRICE PREDICTION USING MACHINE LEARNING Prof. J. Kalidass1, T. Dharshalini2, R. Nivetha3, AP. Subasri4 1Assistant Professor, Department of CSE, Government College of Engineering, Srirangam, Tamilnadu, India 2,3,4UG student, Department of CSE, Government College of Engineering, Srirangam, Tamilnadu, India
---------------------------------------------------------------------***--------------------------------------------------------------------application of Random Forests and Gradient Boosting Abstract - House Price Prediction focuses on the
algorithms aims to explore their effectiveness in capturing the relationship between features and target value, thus facilitating accurate predictions [7]. The proposed system employs experimental analysis and real-world data comparison to elucidate the strengths and weaknesses of Random Forests [1] [2] and Gradient Boosting [3] for house price prediction. By describing the performance characteristics and trade-offs associated with these algorithms, the proposed system aims to provide information that can inform decision making processes for stakeholders in the real estate industry. Finally, this research helps to develop state-of-the-art algorithms using machine learning for practical applications with implications for improving the efficiency and accuracy of the house price prediction model.
development of methods that use machine learning algorithms to accurately predict house prices. Random Forest and Gradient Boosting algorithms have lower mean square error (MSE) and are chosen as the best algorithms for predicting house price. Random forest algorithms handle relationships and provide reliable predictions. Gradient boosting algorithm is used to process large amounts of data to make accurate predictions. Ensemble combines all these individual predictions to produce a final and more accurate prediction. The house information in the dataset also helps improve the estimated house price. This system will help people in the real estate market to make more informed decisions when buying or selling a house. Keywords: Random Forest, Gradient Boosting, Machine Learning, Mean Square Error (MSE).
2. RELATED WORK
1. INTRODUCTION
The House Price Prediction Using Machine Learning Techniques by John Smith, et al., [8] explores the use of machine learning algorithms to forecast housing prices by analysing factors like location, property features, and economic indicators. Researchers collect and preprocess large datasets of real estate transactions, then train machine learning models to predict prices based on these factors. Key challenges include feature selection and addressing data sparsity, with techniques like regression, decision trees, and neural networks commonly used to improve accuracy. Overall, the research aims to provide practical applications in real estate investment, property valuation, and urban planning.
Predicting house prices is an important task in real estate market that affects the decisions of many stakeholders, from home buyers to sellers and investors. Traditional price predictions are often based on historical trends, comparisons and expert opinions. However, these methods may not capture the dynamic and non-linear relationships that exist in the real estate market. Machine learning can predict key values using various data points. This may include features such as location, square footage, number of bedrooms and bathrooms, lot size, and other features that may affect the price. This system will assimilate all these features using machine learning algorithms such as Random Forest [1] [2] and Gradient Boosting [3], providing better house price predictions than traditional methods. This helps buyers and sellers to make better decisions and negotiate better prices. House price prediction using machine learning algorithms is a powerful tool for accurate house price prediction. Machine learning algorithms can be used to identify patterns and relationships in large data sets. With the help of machine learning algorithms, investors and property owners can leverage insights from models to make more informed decisions. The emergence of machine learning algorithms has changed the definition of predictive modeling. Among these algorithms, combinations [4] [5] such as Random Forest [1] [2] and Gradient Boosting [3] have received widespread attention due to their ability to improve the intelligence of multiple decision trees to increase the accuracy of prediction [6]. In this system, the
© 2024, IRJET
|
Impact Factor value: 8.226
Predicting House Prices Using Support Vector Machines by Andrew Wang, et al., [9] explores the use of Support Vector Machines (SVM) to forecast house prices. It likely covers how SVMs can be trained on housing datasets to predict prices accurately, discussing preprocessing methods, kernel functions, and hyper parameter tuning. The paper aims to demonstrate SVM's effectiveness in real estate prediction and may offer insights into best practices for applying SVMs in this context. A Comparative Study of Regression Models for House Price Prediction by John Smith, et al., [10] Emily Johnson, et al., compares different regression techniques for predicting house prices. It evaluates models such as linear regression, ridge regression, lasso regression, and elastic net regression, analysing their predictive accuracy, robustness, and
|
ISO 9001:2008 Certified Journal
|
Page 1351