Old MathJax webview

from the above mentioned study provide the conclusions

.

It can be also be noticed from Table 5 that ensemble algorithms showed the best performance when data is completely balanced (8357 negative and 8.357 positive cases). As expected. Decision Tree algorithm showed the worst results especially when the data is imbalanced (111.911 positive and 8.357 negative cases) in the second experiment we used feature weighting techniques (Evolutionary and PSO) in order to identify the most influential attributes, and hopefully to improve model's performance in order to prevent overtraining of models (because of optimization of attribute selection) we used Wrapper X-Validation operator that divides data on training and test samples. Training sample is used for estimating performance of different classifiers on different feature subsets. Models built on features with best estimated performance are returned to Wrapper X validation and evaluated on unseen data Bagong Tree 0.4 0 06 0.4 In Table 6 the results for evolutionary feature weighing are showed Table 6: Evolutionary feature weighting Attributes Random Bayesian Mata Nive Decision For Boosting Cose Beyes Proton RevolvingUtilization of Unsecuredlines 1 1 02 1 1 1 Age Discretized 0 0 0.4 0.4 0 0 DebRatio 0 0.6 0 0 0 0.8 MonthlyIncome 1 0.61 Debe O 0.6 0.4 04 0.4 0 NumberOpenCreditLinesAndLoans 1 0.8 0 06 06 1 02 Number Real EstateLoans OrLines 0 0.8 1 02 02 0 WagesPerCapita 0.6 0.2 0.8 0.8 0.4 Cumulativelateness 0.4 1 1 0 0 0.8 AUC 0.788 0.744 0.716 0.779 0.771 0.757 15 can be seen from Evolutionary feature weighting that Bayesian Boosting gave the best performance by the means of AUC (0.788) and the most important features were Revolving Utilization of unsecured Lines Monthly income. Cumulativelateness is interesting to notice that Revolving Utilization unsecuredines and Monthly income had the highest relative importance in 5 out of 7 algorithms, and this indicates that these attributes are generally important for this problem. In Table 7 the results for PSO feature weighting are showed 1 1 0.744 It can be seen from PSO feature weighting that perceptron gave the best result (around 0.8) PSO gave the highest weights for Debt and WagesPerCapita while the attributes with lowest importance were Monthly income and Number Real EstateloansOrlines (below O 2) Similar performance (0.796) was obtained by Random Forest (0.796). but the most important attributes were Cumulative Lafence and Revolving Utilization Unsecured Lines, while the lowest weight was Revolving Utilization of insecured Lines Sa general conclusions about most important features cannot be made since other features were often identified as important in the other algorithms (eg AgeDiscretized was the most important feature in Bayesian Boosting and Bagging, while Debt was most important feature for Naive Bayes and Perceptron) From previous results and discussion we can conclude that RevolvingUnlization of Unsecured Lines has the biggest influence on the problem (by both PSO and Evolutionary algorithms). Monthly income also showed high relative importance in Evolutionary, but very low with PSO. In contrast to Evolutionary algorithm PSO gave higher importance to Debt instead of Monthly income