Credit card fraud detection through machine learning

Credit Card Fraud Detection using Machine
learning
Data Alcott Systems
Ph/ Whatsapp 9600095046
Check demo: www.finalsemprojects.com
Data Alcott Systems Contact 9600095046

Due to increase of fraud which results in loss of money across the globe, several
methodologies and techniques developed for detecting frauds Fraud detection involves
analysing the activities of users in order to understand the malicious behaviour of users.
Malicious behaviour is a broad term including delinquency, fraud, intrusion, and account
defaulting. This paper presents a survey of current techniques used in credit card fraud
detection and evaluates a new hybrid approach to identify fraud detection. In the proposed
work, we analyze credit card fraud detection using machine learning algorithm namely logistic
regression and Decision Tree. To make the learning process efficient, we used Principal
component for feature selection.
Abstract

Algorithm Used
 Principal component analysis
 Feature selection
 Decision Tree and Regression
 Decision Tree and Regression used for fraud detection

Introduction
 With the emerging rise of technology today, the dependency on e-commerce and the online
payments has grown exponentially. As the credit card provides convenience to the users but frauds
caused due to these activities causes inconvenience. The credit card information is confidential,
the bank and the other financial enterprises doesn't want to disclose the information about their
customers. Risk management is critical for financial enterprises to survive in such competing
industry. The provisional loss arises due to the “bad” accounts bank lends the money to customers
who eventually do not have capability to pay back. In the risk management, the chances of false
negative (false “good” accounts) could still be high. However, by leveraging their performance such
as credit card utilization, payment information, risks can further be managed to control
provisional loss. In this paper, a focus on risk management as well as fraud detection is depicted.

Figure: Overview of Machine learning

Existing System
 Advanced oversampling methods like SMOTE generate synthetic training instances from
the minority class by interpolation, instead of sample replication.
 The weighting strategy of AdaBoost is equivalent to resampling the data space [6], which
are applicable to most classification systems without changing their learning methods.
 Bahnesonet. al in expanded the transaction aggregation strategy, and proposed to create
a new set of features based on analyzing the periodic behavior of the time of a
transaction using the vonMises distribution. Then, using a real credit card fraud data set
provided by a large European card processing company.
 Halvaieeet. al in addressed credit card fraud detection using Artificial Immune Systems
(AIS), and introduced a new model called AIS-based Fraud Detection Model (AFDM).
The author used an immune system inspired algorithm (AIRS) and improved it for fraud
detection.

Disadvantages
 AIS optimized the data and learning rate but the accuracy arrived is less.
 Different sets of features had an impact on the results.
 SOMTE drawbacks is that undersampling may lose some potential
information, and oversampling may lead the overfitting.
 AdaBoost is mostly used classification whereas extra learning cost is a burden.

Proposed System
 Credit card logs mining is one of the most significant fields in the
area of data mining. There have been a large number of data mining
algorithms rooted in these fields to perform different data analysis
tasks.
 Apply Principal component analysis algorithm to find best features,
then apply decision tree classifier for credit card fraud prediction.

Advantages
 Best accuracy for the study
 PCA gets best features

SYSTEM REQUIREMENTS
 Software Requirements
1. Windows Xp, Windows 7(ultimate, enterprise)
2. Python 3.6 and related libraries
 Hardware Components
1. Processor – i3
2. Hard Disk – 5 GB
3. Memory – 1GB RAM

SYSTEM ARCHITECTURE

IMPLEMENTATION
 The proposed work is implemented in Python 3.6.4 with libraries scikit-
learn, pandas, matplotlib and other mandatory libraries. We downloaded
dataset from kaggle.com. The data downloaded contains train set and test
set separately with two different classes 0 and 1. The traindataset
considered as train set and testdataset considered as test set. Machine
learning algorithm is applied such as logistic regression and DT used.

DATA PRE-PROCESSING
 We have taken multiple attribute in our case study, dataset 16 features/
attributes are taken fr study. Pre-processing of dataset is done for
converting the string attributes to numerals and missing data records are
dropped. The pre-processed data is stored in “dataset.csv” file, which is
given as input for machine learning models.

Principal component analysis feature selection
 Principal Component Analysis, or PCA, is a dimensionality-reduction
method that is often used to reduce the dimensionality of large data sets,
by transforming a large set of variables into a smaller one that still
contains most of the information in the large set.
 Reducing the number of variables of a data set naturally comes at the
expense of accuracy, but the trick in dimensionality reduction is to trade a
little accuracy for simplicity. Because smaller data sets are easier to explore
and visualize and make analyzing data much easier and faster for machine
learning algorithms without extraneous variables to process.

EXPERIMENTAL RESULTS AND EVALUATIONS
 Implemented two machine learning algorithm on the given dataset for
credit card fraud detection shows that Logistics regression model
outperforms other models. The accuracy of Regression is high compared
to decision tree classification machine learning algorithms.
Algorithm Accuracy
Decision Tree 71.41
Logistic Regression 79.91

Metrics

CONCLUSION
 In this study, a new method for data generation of imbalanced data set's
minority class was proposed to enhance fraud detection in credit card by
machine learning and PCA algorithm as an oversampling strategy.
 Although PCA algorithms have been applied in many areas, our
application domain aims to handle imbalanced data set issue by
generating new minority class instances to gain new training sets.
Applying this algorithm into bank credit card fraud detection system aims
to reduce fraudulent transaction and decrease the number of false alert.

FUTURE ENHANCEMENTS
 A further work is to implement this approach using python programming
language, this will allow us to validate our work and produce pertinent
experimental results.

REFERENCES
 [1] H. Lei et al., `À deeply supervised residual network for HEp-2 cell classification via cross-modal transfer learning,'' Pattern Recognit.,
vol. 79, pp. 290 302, Jul. 2018.
 [2] P. Wang, L. Li, Y. Jin, and G. Wang, ``Detection of unwanted traffic congestion based on existing surveillance system using in freeway
via a CNN-architecture trafficNet,'' in Proc. 13th IEEE Conf. Ind. Electron. Appl., May/Jun. 2018, pp. 1134 1139.
 [3] X. Zhu, Y.Wang, J. Dai, L. Yuan, and Y.Wei, ``Flow-guided feature aggregation for video object detection,'' in Proc. ICCV, Mar. 2017, pp.
408 417.
 [4] Z. Zhao,W. Chen, X.Wu, P. C. Chen, and J. Liu, ``LSTM network: A deep learning approach for short-term traffic forecast,'' IET Intell.
Transp. Syst., vol. 11, no. 2, pp. 68 75, Mar. 2017.
 [5] P. Li, D. Wang, L. Wang, and H. Lu, ``Deep visual tracking: Review and experimental comparison,'' Pattern Recognit., vol. 76, pp.
323 338, Apr. 2018.
 [6] P. Wang and J. Di, ``Deep learning-based object classification through multimode fiber via a CNN-architecture SpeckleNet,'' Appl.
Opt., vol. 57, no. 28, pp. 8258 8263, 2018.
 [7] J. Zhao, Z. Zhang, W. Yu, and T.-K. Truong, `À cascade coupled convolutional neural network guided visual attention method for ship
detection from SAR images,'' IEEE Access, vol. 6, pp. 50693-50708, 2018.
 [8] T. Pamula, ``Road traffic conditions classification based on multilevel filtering of image content using convolutional neural
networks,'' IEEE Intell. Transp. Syst. Mag., vol. 10, no. 3, pp. 11 21, Jun. 2018.
 [9] M. Barth and K. Boriboonsomsin, `Ènvironmentally beneficial intelligent transportation systems,'' IFAC Proc. Volumes, vol. 42, no.
15, pp. 342 345, 2009.
 [10] A. Krizhevsky, I. Sutskever, and G. E. Hinton, `Ìmagenet classification with deep convolutional neural networks,'' in Proc. Adv.
Neural Inf. Pro-cess. Syst., 2012, pp. 1097 1105.

Thank You

Credit card fraud detection through machine learning

More Related Content

What's hot (20)

Similar to Credit card fraud detection through machine learning (20)

More from dataalcott (20)

Recently uploaded (20)

Credit card fraud detection through machine learning