Dynamic Stacked Ensemble with Entropy based Undersampling for the Detection of Fraudulent Transactions

Laveti, Ramesh Naidu; Mane, Abhay Anand; Pal, Supriya N.

doi:10.1109/i2ct51068.2021.9417896

Cited by 2 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…EL is being extensively experimented with in OCCF detection research. [26] EL is a combination of two or more ML algorithms to solve a computational problem better than would have been done when the algorithms were trained in silos. [27][28][29][30] Due to the technological advancements, the domain is now well associated with big data rendering traditional rule-based less effective when dealing with huge datasets.…”

Section: Introductionmentioning

confidence: 99%

Bibliometric Analysis of Recent Trends in Machine Learning for Online Credit Card Fraud Detection

Hove,

Olugbara,

Singh

2024

J Scientometric Res.

View full text Add to dashboard Cite

Online credit card fraud (OCCF) is the malicious act of using credit card details belonging to another person to complete fraudulent transactions over the Internet. Naturally, masses of researchers have engaged in the imperative search for effective solutions across a wide range of disciplines. The result is a rich tapestry of methodologies, models, frameworks, and inventions exhibiting dramatic spread and growth. However, this also results in an unorganized research domain. In this state, a bibliometric analysis is a useful technique for establishing a reconciled snapshot of the OCCF research domain. This paper has particular interest in determining the intellectual structure of the knowledge of machine learning, deep learning, and ensemble learning models for early detection of OCCF. This bibliometric analysis is conducted using 524 publications between 2013 and 2022 extracted from the SCOPUS core collection database. Microsoft Excel, VOSViewer, and Biblioshiny software tools were used for data analysis. The findings indicate that ensemble learning models are trending and the three most authoritative authors have been exposed in this study. There is a sharp rise in global publications annually and India has the most publications with the most impactful authors. Five broad clusters of knowledge are imbalanced data, anomaly detection, machine learning, decision trees, and ensemble learning. Intellectual collaboration across regions is strong amongst Asia, Europe, and North America with weak associations between Africa and South America. This is the first bibliometric analysis in the domain of OCCF detection to the best of the author's ability. The findings significantly contribute to the application of OCCF detection through the creation of intellectual patterns in existing literature. The results bring about synthesis within a domain of research that is currently disorganized. This in turn helps researchers to identify research gaps, and areas for further research and formulate a curriculum.

show abstract

Section: Introductionmentioning

confidence: 99%

Bibliometric Analysis of Recent Trends in Machine Learning for Online Credit Card Fraud Detection

Hove,

Olugbara,

Singh

2024

J Scientometric Res.

View full text Add to dashboard Cite

show abstract

Balancing Imbalanced Toxicity Models: Using MolBERT with Focal Loss

Masood,

Kaski,

Ceulemans

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Drug-induced liver injury (DILI) presents a multifaceted challenge, influenced by interconnected biological mechanisms. Current DILI datasets are characterized by small sizes and high imbalance, posing difficulties in learning robust representations and accurate modeling. To address these challenges, we trained a multi-modal multi-task model integrating preclinical histopathologies, biochemistry (blood markers), and clinical DILI-related adverse drug reactions (ADRs). Leveraging pretrained BERT models, we extracted representations covering a broad chemical space, facilitating robust learning in both frozen and fine-tuned settings. To address imbalanced data, we explored weighted Binary Cross-Entropy (w-BCE) and weighted Focal Loss (w-FL) . Our results demonstrate that the frozen BERT model consistently enhances performance across all metrics and modalities with weighted loss functions compared to their non-weighted counterparts. However, the efficacy of fine-tuning BERT varies across modalities, yielding inconclusive results. In summary, the incorporation of BERT features with weighted loss functions demonstrates advantages, while the efficacy of fine-tuning remains uncertain.

show abstract

Dynamic Stacked Ensemble with Entropy based Undersampling for the Detection of Fraudulent Transactions

Cited by 2 publications

References 26 publications

Bibliometric Analysis of Recent Trends in Machine Learning for Online Credit Card Fraud Detection

Bibliometric Analysis of Recent Trends in Machine Learning for Online Credit Card Fraud Detection

Balancing Imbalanced Toxicity Models: Using MolBERT with Focal Loss

Contact Info

Product

Resources

About