Novel classification to detect metro water fraudulent in houses using naive bayes and comparison of prediction accuracy with decision tree analysis algorithms.

Autor:	Sreekanth, D., Thinakaran, K.
Předmět:	DECISION making DECISION trees TREE size ALGORITHMS FRAUD FORECASTING
Zdroj:	AIP Conference Proceedings; 2023, Vol. 2821 Issue 1, p1-7, 7p
Abstrakt:	The research is to predict metro water fraud accurately by Decision Tree Algorithm and compare the prediction accuracy with Naive Bayes Algorithm. In the existing system Naive Bayes algorithm is used and in the proposed system Decision Tree algorithm is used. In Naive Bayes with sample size = 20 and Decision Tree with sample size = 20 was iterated for predicting the accuracy. Here the Pre-power test is about 80%. The algorithms have been implemented and tested over a dataset which consists of 8002 records. After performing the experiment, the mean accuracy of the Decision Tree algorithm is 99.61% and the accuracy of Naive Bayes algorithm is 65.42% for metro water fraudulent prediction. There is a statistically significant difference in accuracy for two algorithms is p<0.05 by performing independent samples t-tests. The comparison results show that the Decision Tree algorithm is significantly better than the Naive Bayes algorithm. [ABSTRACT FROM AUTHOR]
Databáze:	Complementary Index
Externí odkaz:	Zobrazit plný text záznamu