International Journal of Recent Technology and Engineering (IJRTE) ISSN: 2277-3878, Volume-8 Issue-4, November 2019 1477 Published By: Blue Eyes Intelligence Engineering & Sciences Publication Retrieval Number: D7621118419/2019©BEIESP DOI:10.35940/ijrte.D7621.118419 Abstract: With the fast moving technological advancement, the internet usage has been increased rapidly in all the fields. The money transactions for all the applications like online shopping, banking transactions, bill settlement in any industries, online ticket booking for travel and hotels, Fees payment for educational organization, Payment for treatment to hospitals, Payment for super market and variety of applications are using online credit card transactions. This leads to the fraud usage of other accounts and transaction that result in the loss of service and profit to the institution. With this background, this paper focuses on predicting the fraudulent credit card transaction. The Credit Card Transaction dataset from KAGGLE machine learning Repository is used for prediction analysis. The analysis of fraudulent credit card transaction is achieved in four ways. Firstly, the relationship between the variables of the dataset is identified and represented by the graphical notations. Secondly, the feature importance of the dataset is identified using Random Forest, Ada boost, Logistic Regression, Decision Tree, Extra Tree, Gradient Boosting and Naive Bayes classifiers. Thirdly, the extracted feature importance if the credit card transaction dataset is fitted to Random Forest classifier, Ada boost classifier, Logistic Regression classifier, Decision Tree classifier, Extra Tree classifier, Gradient Boosting classifier and Naive Bayes classifier. Fourth, the Performance Analysis is done by analyzing the performance metrics like Accuracy, FScore, AUC Score, Precision and Recall. The implementation is done by python in Anaconda Spyder Navigator Integrated Development Environment. Experimental Results shows that the Decision Tree classifier have achieved the effective prediction with the precision of 1.0, recall of 1.0, FScore of 1.0 , AUC Score of 89.09 and Accuracy of 99.92%. Index Terms: Machine Learning, Recall, FScore, Accuracy and AUC Score. I. INTRODUCTION In machine learning, the prediction of fraud credit card transaction is done either by regression or classification process. The entire nation is moving towards online transactions through credit card payment and it is possible Revised Manuscript Received on November 15, 2019 M. Shyamala Devi, Associate Professor, Computer Science and Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, Chennai, TamilNadu, India. Nariboyena Vijaya Sai Ram, III Year B.Tech Student, Computer Science and Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, Chennai, TamilNadu, India. Aravapalli Sai Vamshi, III Year B.Tech Student, Computer Science and Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, Chennai, TamilNadu, India. Basyam Bharath, III Year B.Tech Student, Computer Science and Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, Chennai, TamilNadu, India. Mallangi Surya Prakash Reddy, III Year B.Tech Student, Computer Science and Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, Chennai, TamilNadu, India. due to the technological growth. Fraud online transaction is one of the criminal activities and it must be found at the source itself. This lead to the usage of machine learning approach for the prediction and analysis of transactions. The paper is organized in which the literature survey is dealt with Section 2 followed by the proposed work in the Section 3. Implementation and the performance analyis is discussed in Section 4 followed by the conclusion of the paper in Section 5. II. RELATED WORK A. Literature Survey The dimensionality reduction can be done by the feature extraction and selection and is considered in predicting the target variable [1]. The general policy regulations, rules and standards are also considered in predicting the target variable [2]. The prediction of the target variable for credit card transaction is done with the classification methods and it is used to categorize the class of transaction [3]. The markov model is used for predicting the fraud credit card and debit card online transaction [4]. The analysis of the whole online credit card data is needed for predicting the online fraud detection and the machine learning approaches can be used to implement this [5]. Several data mining tools and approaches can be used for predicting the credit card fraud detection. The manual computation of detecting the fraud credit card online transaction detection is a tedious and time consuming process and it lead to impractical condition [6]. The fraud in the credit card transaction can be due to inner and outer environment and the fraud may be due to the credit card stole and unusual way of handling the online transaction [7]. The machine learning feature selection and feature extraction methods can be used for the prediction of any factor in different application can be learnt through this article [8] – [21]. III. PROPOSED WORK In this paper, we have used machine learning classification algorithm for predicting the fraudulent credit card transaction. Our contribution of predicting fraudulent credit card transaction is done in four ways. (i) Firstly, the relationship between the variables of the dataset is identified and represented by the graphical notations. Swindling Shonky Anatomization of Credit Card Transactions using Machine Learning M. Shyamala Devi, Nariboyena Vijaya Sai Ram, Aravapalli Sai Vamshi, Basyam Bharath, Mallangi Surya Prakash Reddy