Ponte Academic Journal Sep 2016, Volume 72, Issue 9 |
A NOVEL FRAMEWORK FOR IMPROVING CLASS IMBALANCE LEARNING ON FINANICAL FRAUD DETECTION Author(s): R. Buli Babu ,Dr. Mohammed Ali Hussain J. Ponte - Sep 2016 - Volume 72 - Issue 9 doi: 10.21506/j.ponte.2016.9.37 Abstract: Today�s real word data posses class imbalanced datasets of which most of the instances are converged to a single class and few others instances assigned to smaller. To build classification models from imbalanced datasets is much harder and has a challenging task in solving Machine-learning algorithms. Traditional classification algorithms use similarity property in category minor and major classes. Real world imbalanced data can be classified accurately into class of major and poor class accuracy of minor by developing models which uses Machine learning algorithms to find the correct accuracy. We propose a framework evaluation model which classifies fraud detection on real-world imbalance data sets for imbalance dataset to achieve good majority class accuracy and poor minor accuracy. The evaluation of the framework is done using 7 Machine Learning Classification Algorithms with advanced balanced techniques. Many of the ideas are taken from the literature study. Most of our work is done using advanced balanced techniques using financial datasets of primary class to identify the accuracy and improve it using the entire algorithm and tested with results. The results obtained from shows that recall and precision are effectively used for measuring the developed model for imbalanced datasets. We also suggest use data mining techniques in simplifying balance datasets before, solving huge imbalance class problems using our framework
|
Download full text: Check if you have access through your login credentials or your institution |
|
Guide for Authors
This guideline has been prepared for the authors to new submissions and after their manuscripts have been accepted |
Authors Login
We welcome refrees who would be willing to act as reviewers |
Paper Tracking
You can track your submitted article from this tab |
Editorial Board
The international editorial board is headed by Dr. Maria E. Boschi |
General Policies
Papers that are published or held by the Journal may not be published elsewhere |
Peer Review Process
Papers will be sent to three peer reviewers for evaluation |