An Advanced House Price Detection Using Novel Classification with Linear Regression by Comparing Predictable Over Actual Pricing

This study presents an innovative approach to predicting housing prices by integrating novel classification techniques with an optimized Linear Regression (LR) algorithm. The objective is to bridge the gap between predicted and actual housing values. We operationalized this by defining two distinct groups: Group 1, representing prices predicted by the LR model, and Group 2, indicating the actual market prices. A total of 20 data samples were evaluated, equally divided between the two groups. Our advanced LR methodology's performance was assessed using statistical metrics including the Correlation Coefficient, Mean Absolute Error (MAE), and Mean Squared Error (MSE). Results indicated a statistically significant improvement in the LR algorithm's accuracy, with a p-value of 0.0301 indicating significance (p < 0.05), an MSE of 0.0325, and an MAE of 0.0362. Comparative analysis shows that our Novel LR algorithm outperforms existing models in identifying pricing issues in the housing market.