International Journal of Science, Engineering and TechnologyAuthors: Akinmerese, Oluwatobi, Ifekandu, Chiamaka, Ezeoke, Evelyn, Osuji, Adaeze, Lawal, Esther
Abstract: Reliable methods for forecasting home prices are scarce in many areas, particularly in our nation. This research tackles this gap by applying machine learning techniques to anticipate house values based on key attributes. Using the Cross Industry Standard Process for Data Mining (CRISP-DM) framework as a reference, this research used the Linear Regression model. Data cleansing, feature selection and visualization were all part of the approach. It was found that accuracy increased when the dataset was transformed using logarithmic values and models were assessed using statistical techniques like p-values and the Bayesian Information Criterion (BIC). The results demonstrate that property prices may be accurately forecasted using a condensed dataset without sacrificing model performance.
DOI: http://doi.org/10.5281/zenodo.17786493
