Exploring House Price Forecasting through Machine Learning and Data Preprocessing

Predicting house prices accurately is crucial in real estate, influencing decisions for buyers, sellers, and investors. Machine learning has emerged as a potent tool in this domain, leveraging historical sales data, property features, and economic indicators to forecast future prices. However, the e...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2024 4th International Conference on Pervasive Computing and Social Networking (ICPCSN) s. 304 - 310
Hlavní autoři: Vaishnavi, A.V.S.S.P.L., Raghavendra, G. Gopi Krishna, Jilan, Mohammed, Chowdary, A. Pranya, Singh, Romen, C, Karthikeyan
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 03.05.2024
Témata:
Accuracy
Biological system modeling
Data integrity
Data preprocessing
Deep learning
Feature extraction and feature engineering
House price prediction
Machine learning
Machine learning algorithms
Normalization
Symbiosis
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Predicting house prices accurately is crucial in real estate, influencing decisions for buyers, sellers, and investors. Machine learning has emerged as a potent tool in this domain, leveraging historical sales data, property features, and economic indicators to forecast future prices. However, the efficacy of machine learning models hinges on data quality, necessitating meticulous preprocessing steps such as cleansing, normalization, and feature engineering. Through techniques like data filtration and normalization, preprocessing refines data suitability for algorithms, enhancing predictive accuracy. In this study, we illustrate the transformative impact of preprocessing on predictive models' reliability. By contrasting accuracy tables for preprocessed and non-preprocessed datasets, we demonstrate the tangible benefits of preprocessing in refining predictive outcomes. The findings highlight the symbiotic relationship between machine learning algorithms and preprocessing techniques, emphasizing their crucial role in enhancing predictive capabilities in the dynamic real estate market landscape.
DOI:10.1109/ICPCSN62568.2024.00055