Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
2023 Second International Conference on Augmented Intelligence and Sustainable Systems (ICAISS), 2023, p.954-959
Ort / Verlag
IEEE
Erscheinungsjahr
2023
Link zum Volltext
Quelle
IEL
Beschreibungen/Notizen
The precise prediction of house prices is highly significant for professionals in the real estate industry, homeowners, and potential buyers. This study primarily focuses on utilizing the random forest algorithm to accurately predict house prices. A comprehensive dataset containing various features such as location, size, rooms, amenities, and historical transaction data was collected. The investigation included steps of data conditioning, designing features, instruction of models, and oversight. To assess the outcome of the model along with avoiding the situation a random-forest stance was employed, and validated cross-valid techniques were employed. Lasso regression is employed to identify the key features that significantly influence house prices. Results showed promising predictive accuracy, surpassing other baseline algorithms. Feature importance analysis highlighted the significant influence of location, size, and the number of rooms on house prices, aligning with domain knowledge. This study illustrates the precision of random forests and Lasso-regression-based ML assertions, assisting housing specialists, homeowners, and potential purchasers in making accurate choices. Future research can explore integrating additional data sources and advanced techniques to enhance prediction accuracy and address housing market challenges.