Prediction Of Default Credit Card Users Using Data Mining Techniques
Akanksha Shankar Shetty1, Manoj R2
1Akanksha Shankar Shetty, Department of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India.
2Manoj R, Department of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India.
Manuscript received on 05 May 2019 | Revised Manuscript received on 12 May 2019 | Manuscript published on 30 May 2019 | PP: 816-821 | Volume-8 Issue-7, May 2019 | Retrieval Number: G5754058719/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Development of financial sector has lead to an increase in financial risk. In order to prevent such risks, this study proposes a model for prediction of default cards with the help of data mining techniques. Balancing algorithms such as SMOTE and ADASYN algorithms are used to balance the imbalanced data because balanced data can be useful in increasing the efficiency of the model. Later both the balancing techniques are compared to see which one performs better. This balanced data is then taken as an input to an machine learning algorithm such as SVM to predict default credit cards. Accuracy of this model is found out by comparing it with other data models.
Keyword: Default credit cards, prediction model, data mining, classification, machine learning.
Scope of the Article: Machine Learning