Rice Quality Analysis Prediction Using the Canny Algorithm in a Novel Way and Accuracy Comparison with Image Processing Techniques

Abstract

Aim: The main aim of the research is to predict loans using Random Forest (Random Forest) over XGBoost Algorithm (XGBoost). Materials and Methods: Random Forest and XGBoost are implemented in this research work. Sample size is calculated using G power software and determined as 10 per group with pretest G power value of 80%, and the data has been collected from various web sources with recent study findings and threshold 0.05% and confidence interval 95%. Result and Discussion: Random Forest provides a higher of 85.30% compared to XGBoost algorithm with 75.10% in predicting loan. There is a significant difference between two groups with insignificance value of p = 0.941; p >0.05. Conclusion: The results show that Novel Random Forest algorithm for loan prediction appears to generate better accuracy than XGBoost