TY - JOUR
T1 - Balancing Act
T2 - Tackling organized retail fraud on e-commerce platforms with imbalanced learning text models
AU - Mutemi, Abed
AU - Bação, Fernando
N1 - Mutemi, A., & Bação, F. (2024). Balancing Act: Tackling organized retail fraud on e-commerce platforms with imbalanced learning text models. International Journal of Information Management Data Insights, 4(2), 1-13. Article 100256. https://doi.org/10.1016/j.jjimei.2024.100256
PY - 2024/11
Y1 - 2024/11
N2 - As online shopping expands rapidly, so does the prevalence of fraud, resulting in significant losses for retailers. According to the 2020 National Retail Federation (NRF) report, organized retail crime costs retailers nearly $800,000 per billion in sales, with an expected global annual increase of over fourteen percent. This paper introduces a text-based fraud detection framework to mitigate these losses efficiently. The framework comprises four key components: text preprocessing, representation, knowledge extraction via machine learning algorithms, and model evaluation. By integrating data augmentation techniques, the framework enhances classifier performance in detecting fraud. The proposed method, employing a combination of FastText and Random Forest classifiers, achieves an impressive F1 score of 0.833 and AUC score of 0.99 on an augmented dataset, surpassing conventional keyword-based models. Informed by best practices in fraud detection, this scalable framework promises a solution to combat the escalating fraud associated with the exponential growth of online shopping.
AB - As online shopping expands rapidly, so does the prevalence of fraud, resulting in significant losses for retailers. According to the 2020 National Retail Federation (NRF) report, organized retail crime costs retailers nearly $800,000 per billion in sales, with an expected global annual increase of over fourteen percent. This paper introduces a text-based fraud detection framework to mitigate these losses efficiently. The framework comprises four key components: text preprocessing, representation, knowledge extraction via machine learning algorithms, and model evaluation. By integrating data augmentation techniques, the framework enhances classifier performance in detecting fraud. The proposed method, employing a combination of FastText and Random Forest classifiers, achieves an impressive F1 score of 0.833 and AUC score of 0.99 on an augmented dataset, surpassing conventional keyword-based models. Informed by best practices in fraud detection, this scalable framework promises a solution to combat the escalating fraud associated with the exponential growth of online shopping.
KW - Fraud detection
KW - Machine learning
KW - Text classification
KW - E-commerce
KW - Text mining
KW - Natural language processing
KW - Word representation learning
KW - Text data augmentation
UR - http://www.scopus.com/inward/record.url?scp=85195256092&partnerID=8YFLogxK
U2 - 10.1016/j.jjimei.2024.100256
DO - 10.1016/j.jjimei.2024.100256
M3 - Article
SN - 2667-0968
VL - 4
SP - 1
EP - 13
JO - International Journal of Information Management Data Insights
JF - International Journal of Information Management Data Insights
IS - 2
M1 - 100256
ER -