USING ARTIFICIAL NEURAL NETWORKS FOR HOUSE PRICE PREDICTION

The real estate business in our ecosystem has the lowest level of transparency. Prices of homes are consistently fluctuating on a daily basis and, on occasion, are influenced more by speculation than by actual appraisal. The fundamental challenge of our research endeavour is to accurately forecast house prices using real-world factors. In this section, our goal is to make our assessments based on each and every fundamental criterion that is taken into consideration when calculating the price. After receiving training online, the ANN is able to learn from data sets that have been annotated and then generate predictions. For illustration purposes, an ANN was used to develop a regression model of the housing prices in a number of Boston towns in the United States, and it was discovered that the projected results were quite similar to the actual data. We show that the machine learning technique is a beneficial one for predicting property prices in the Chinese market, and we do so by demonstrating our findings. Our findings might be utilised on their own or in conjunction with fundamental forecasts in order to develop perspectives on housing market developments and to undertake policy research. Our empirical approach should not be difficult to deploy, which is an essential factor to a large number of decision makers, and it has the potential to be adapted for the purpose of projecting the housing prices of other citie