An enhanced house prices prediction using novel supervised forest techniques by comparing prediction over actual prices.

The aim of the work is to detect the problems for housing prices to estimate the relationship by Random Forest (RF) algorithm for predictions using supervised techniques. Materials and Methods: Data collection was carried out and the analysis was done in the Google Collab for the execution of results and to estimate the relationship of given algorithms. Proposed work involves two groups for detection of problems for housing prices. Group 1 was the predicted price and Group 2 was the actual price performed by the Random Forest (RF) algorithm. The sample size was calculated. It was identified that 10 samples/group and 20 samples were taken totally. The improved Random Forest (RF) machine learning technique is used for predicting the accuracy based on Coefficient of Determination (CD), Mean Square Error (MSE), Mean Absolute Error (MAE). Results and Discussion: The significant difference of Random Forest (RF) algorithm (p <0.05), in is 0.0372, MSE is 0.0332 and MAE is 0.0355. Conclusion: The data was collected from various resources for the detection of problems for housing prices to estimate the relationship. The Novel Random Forest (RF) algorithm obtains better performance when analyzed with other existing algorithms in detection of problems for housing prices. [ABSTRACT FROM AUTHOR]