The Feasibility of Credit Using C4.5 Algorithm Based on Particle Swarm Optimization Prediction

Siswanto Siswanto, Abdussomad Abdussomad, Windu Gata, Nia Kusuma Wardhani, Grace Gata, Basuki Hari Prasetyo


Credit is a belief that one is given to a person or other entity which is concerned in the future will fulfill all the obligations previously agreed. The objective of research is necessary to do credit analysis to determine the feasibility of a credit crunch, through credit analysis results, it can be seen whether the customer is feasible or not. The methods are is used to predict credit worthiness is by using two models, models classification algorithm C4.5 and C4.5 classification algorithm model based Particle Swarm Optimization (PSO). After testing with these two models found that the result C4.5 classification algorithm generates a value of 90.99% accuracy and AUC value of 0.911 to the level diagnostics Classification Excellent, but after the optimization with C4.5 classification algorithm based on Particle Swarm Optimization accuracy values amounted to 91.18% and the AUC value of 0.913 to the level of diagnosis Excellent Classification. These both methods have different accuracy level of 0.18%.


credit analysis; C4.5 algorithm; particle swarm optimization

Full Text: PDF


  • There are currently no refbacks.