Machine Learning for Credit Card Fraud Detection

Gao, Yuxin; Zhang, Shuoming; Lü, Jian

doi:10.1145/3473714.3473749

Cited by 7 publications

(6 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such disparities in the accuracy of prediction may have been expected and are normal -due to errors of false-positives, true-negatives, false-negatives, and true-negatives in agreement with [61], [129]- [131] as in Table 2 and figure 1. The ensemble during the retraining or cross-validation phase -over a series of iterations (movement) yields an accuracy prediction of 99.6 percent (i.e.…”

Section: Training Performance Evaluationmentioning

confidence: 52%

StreamBoostE: A Hybrid Boosting-Collaborative Filter Scheme for Adaptive User-Item Recommender for Streaming Services

Atuduhor, R.R.,

Okpor, M.D,

3Yoro, R.E.

et al. 2024

AIMS Research Journal

View full text Add to dashboard Cite

With home entertainment, selecting the perfect movie is a pervasive challenge, amplified by many streaming platforms like Netflix and Amazon Prime. This study advances a movie recommender system with collaborative filtering approach as implemented in Python titled StreamBoostE. We used the user-based and item-based similarity schemes on feature embedding to aid faster model construction and training for the tree-based gradient boosting ensemble. Employing both user- and item-based collaborative filtering with cosine similarity to ease feature embedding, the system assesses movies inter-relations via personalized user interest and preferences as submitted user titles with a focus on movie genre classification. Results shows the ensemble yields a recommender prediction accuracy of 0.9984 with F1 of 0.996. The major contribution of StreamBoostE is in its capability to expedite the movie selection process when integrated using flask API and streamlit for cross-channel integration in web-based platforms. It presents users with a list of top-10 recommended movies by genre similarity. The XGBoost ensemble performed best with the user-/item-based collaborative filtering scheme fused with feature embedding approach as a sampling method. Keywords: Random Forest, SMOTE, credit card fraud detection, feature selection, imbalanced dataset Aims Research Journal Reference Format: Atuduhor, R.R., Okpor, M.D., Yoro, R.E., Odiakaose, C.C., Emordi, F.U., Ojugo, A.A., Ako, R.E., Geteloma, V.O., Ejeh, P.O., Abere, R.A., Ifioko, A.M., & Brizimor, S.E. (2024): StreamBoostE: A Hybrid Boosting-Collaborative Filter Scheme for Adaptive User-Item Recommender for Streaming Services. Advances in Multidisciplinary and Scientific Research Journal Vol. 10. No. 2. Pp 89-106. www.isteams.net/aimsjournal. dx.doi.org/10.22624/AIMS/V10N2P8

show abstract

Section: Training Performance Evaluationmentioning

confidence: 52%

StreamBoostE: A Hybrid Boosting-Collaborative Filter Scheme for Adaptive User-Item Recommender for Streaming Services

Atuduhor, R.R.,

Okpor, M.D,

3Yoro, R.E.

et al. 2024

AIMS Research Journal

View full text Add to dashboard Cite

show abstract

“…The hybrid favours the use of a second hidden layer with greater value for f-score, which agrees with the findings. (Gao et al, 2021;Yuan & Wu, 2021;Zareapoor & Shamsolmoali, 2015 Ojugo & Eboka, 2020a;Ojugo & Otakore, 2020a;Ojugo & Yoro, 2020b). Also, 276 cases were incorrectly identified as fraud transactions and as false negative and 233 cases were correctly identified as malicious instances, these were marked as true-negative.…”

Section: Results and Findingsmentioning

confidence: 99%

Pilot Study on Web Server HoneyPot Integration Using Injection Approach for Malware Intrusion Detection

Malasowe,

Aghware,

Edim

2024

AIMS Research Journal

View full text Add to dashboard Cite

The digital world is rapidly coming together as well as transforming a lot of our valued data onto digital forms. Its consequent dissemination eased via the advent of the Internet has also encountered many attacks due to predictable responses from many users – leading up to social engineering and exploits on trust-level of users. The use of deception is now playing a very prominent role in enhancing data security. Several approaches abound to discourage and redirect challenges (via the use of honeypot), and to detect such intrusive activities (via an intrusion detection systems). These have been successfully used to minimize security breaches. We explore a deep learning deception-based honeypot to minimize breaches by adversaries. Used on web servers, it is equipped with identification capabilities as the system learns and defends a user system against intrusive actions. Our confusion matrix shows model has sensitivity of 0.81, specificity 0.08, and prediction accuracy of 0.991 with an improvement rate of 0.39 for data that were not originally used to train. . Keywords: Web Server, HoneyPot, Integratio, Injection Approach, Malware Intrusion Detection CISDI Journal Reference Format Malasowe B., Aghware, F. & Edim, B.E. (2024): Pilot Study on Web Server HoneyPot Integration Using Injection Approach for Malware Intrusion Detection. Computing, Information Systems, Development Informatics & Allied Research Journal. Vol 15 No 1, Pp 13-.28. dx.doi.org/10.22624/AIMS/CISDI/V15N1P2. Available online at www.isteams.net/cisdijournal

show abstract

“…true-positives). The result showed that 31detected cases were erroneously labeled and agreed with [75]- [77] as false-positive; Also, 776 wrongly detected threats (i.e. false-negative) and 283-correctly recognized malicious instances labeled as true-negative.…”

Section: B Discussion Of Findingsmentioning

confidence: 99%

DeLClustE: Protecting Users from Credit-Card Fraud Transaction via the Deep-Learning Cluster Ensemble

Aghware,

Yoro,

Ejeh

et al. 2023

IJACSA

View full text Add to dashboard Cite

Fraud is the unlawful acquisition of valuable assets gained via intended misrepresentation. It is a crime committed by either an internal/external user, and associated with acts of theft, embezzlement, and larceny. The proliferation of credit cards to aid financial inclusiveness has its usefulness alongside it attracting malicious attacks for gains. Attempts to classify fraudulent credit card transactions have yielded formal taxonomies as these attacks seek to evade detection. We propose a deep learning ensemble via a profile hidden Markov model with a deep neural network, which is poised to effectively classify credit-card fraud with a high degree of accuracy, reduce errors, and timely fashion. The result shows the ensemble effectively classified benign transactions with a precision of 97 percent. Thus, we posit a new scheme that is more logical, intuitive, reusable, exhaustive, and robust in classifying such fraudulent transactions based on the attack source, cause(s), and attack time gap.

show abstract

Machine Learning for Credit Card Fraud Detection

Cited by 7 publications

References 1 publication

StreamBoostE: A Hybrid Boosting-Collaborative Filter Scheme for Adaptive User-Item Recommender for Streaming Services

StreamBoostE: A Hybrid Boosting-Collaborative Filter Scheme for Adaptive User-Item Recommender for Streaming Services

Pilot Study on Web Server HoneyPot Integration Using Injection Approach for Malware Intrusion Detection

DeLClustE: Protecting Users from Credit-Card Fraud Transaction via the Deep-Learning Cluster Ensemble

Contact Info

Product

Resources

About