Prediction of bankruptcy using big data analytic based on fuzzy c-means algorithm

Arup Guha


This paper has suggested an optimization approach of the cluster-based sampling using Fuzzy c means algorithm to the classifier in order to select the most appropriate instances of bankruptcy. This method was examined with the help of a clustering method and GA based artificial neural network in order to solve the existing data imbalance issue. The objective of this paper is to optimize the selected design model of GA-ANN by using Fuzzy C means algorithm to predict corporate bankruptcies by considering different financial ratios of companies across several industries within the period from 1994 to 2014. Effectiveness of this method was proved by comparing its accuracy rate with the results of existing method. From the performance result the accuracy rate of this method was found to be 78.2% and misclassification rate to be 0.2178.


Artificial neural network; Cluster-based sampling; Fuzzy c means clustering; Genetic algorithm; Machine learning; Under-sampling technique

Full Text:




  • There are currently no refbacks.

View IJAI Stats

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.