TY - GEN
T1 - Fraud Detection Using Decision Tree Algorithm to Curb Identity Theft
AU - Hai, Tao
AU - Zhou, Jincheng
AU - Ajoboh, Oluwakemi A.
AU - Olatunji, Timothy
AU - Zhou, Xiaoshan
AU - Iwendi, Celestine
AU - Oyesola, Boluwatife
N1 - Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2023
Y1 - 2023
N2 - Identity theft is a growing concern that can cause significant financial and emotional harm to individuals. One way to detect and prevent identity theft is by using machine learning algorithms, such as decision tree. In this study, we investigate the effectiveness of using a decision tree algorithm in detecting and preventing identity theft. A dataset consisting of personal information, as well as information on suspicious activity, was collected from a financial institution. The dataset included a total of 284,807 rows of data and 30 columns. The decision tree algorithm was implemented using the Python programming language and the scikit-learn library. The algorithm was trained on the training set and used to classify new cases as either fraudulent or non-fraudulent. The performance of the decision tree algorithm was evaluated using several performance metrics such as accuracy, precision, recall and F1-score. Results showed that the decision tree algorithm was effective in detecting and preventing identity theft, with an overall accuracy of 99%. These findings demonstrate the potential of using decision tree algorithms in detecting and preventing identity theft, which can help to curb the increasing problem of identity theft and protect individuals from financial and emotional harm.
AB - Identity theft is a growing concern that can cause significant financial and emotional harm to individuals. One way to detect and prevent identity theft is by using machine learning algorithms, such as decision tree. In this study, we investigate the effectiveness of using a decision tree algorithm in detecting and preventing identity theft. A dataset consisting of personal information, as well as information on suspicious activity, was collected from a financial institution. The dataset included a total of 284,807 rows of data and 30 columns. The decision tree algorithm was implemented using the Python programming language and the scikit-learn library. The algorithm was trained on the training set and used to classify new cases as either fraudulent or non-fraudulent. The performance of the decision tree algorithm was evaluated using several performance metrics such as accuracy, precision, recall and F1-score. Results showed that the decision tree algorithm was effective in detecting and preventing identity theft, with an overall accuracy of 99%. These findings demonstrate the potential of using decision tree algorithms in detecting and preventing identity theft, which can help to curb the increasing problem of identity theft and protect individuals from financial and emotional harm.
KW - Decision tree algorithm
KW - F1-score
KW - Fraud detection
KW - Identity theft
KW - Precision
KW - Recall
UR - https://www.scopus.com/pages/publications/85174535959
U2 - 10.1007/978-3-031-37164-6_26
DO - 10.1007/978-3-031-37164-6_26
M3 - Conference contribution
AN - SCOPUS:85174535959
SN - 9783031371639
T3 - Lecture Notes in Networks and Systems
SP - 351
EP - 360
BT - Proceedings of ICACTCE'23—The International Conference on Advances in Communication Technology and Computer Engineering - New Artificial Intelligence and the Internet of Things Based Perspective and Solutions
A2 - Iwendi, Celestine
A2 - Boulouard, Zakaria
A2 - Kryvinska, Natalia
PB - Springer Science and Business Media Deutschland GmbH
T2 - International Conference on Advances in Communication Technology and Computer Engineering, ICACTCE 2023
Y2 - 24 February 2023 through 25 February 2023
ER -