Analysis of third-party request structures to detect fraudulent websites

Gopal, Ram; Hojati, Afrouz; Patterson, Raymond A.

doi:10.1016/j.dss.2021.113698

Cited by 9 publications

(7 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, all the investigations presented in the preceding paragraphs relate to a very narrow range of products. However, as we have said, the issue of counterfeiting has acquired such a magnitude that it already covers very diverse topics (Islam et al, 2021) especially technological fields (Jha, 2023; Su et al, 2022) that help to identify fraudulent websites (Gopal et al, 2022) or to make moral‐theological analysis of unethical business practices (Uroko, 2022).…”

Section: Literature Reviewmentioning

confidence: 99%

A world of counterfeits: Knowledge to decide

Marín‐Palacios,

Botey‐Fullat,

Márquez

2024

J of Consumer Behaviour

View full text Add to dashboard Cite

Counterfeiting has become a major social problem because of the consequences for consumers, businesses and governments. The objective is to describe the current state of counterfeiting research, define the main thematic areas, identify gaps and highlight key findings. A bibliometric analysis of the growing number of publications addressing the counterfeiting problem in the existing literature is conducted. The articles are taken from a search of the Scopus database. After excluding some scientific‐technological subareas, 1984 papers are analyzed, to which 23 outstanding papers were added at a later stage. In more recent years, most of the articles focus on the development of technologies. Four conceptual areas have been identified: technological development, social behavior, economic aspects and legal aspects. The latter two are the least studied. Also identified in the social area are two topics of interest that have been little addressed, namely, the effect of prior purchase experience and the development of theories describing consumer behavior towards counterfeits. The value derived from this research is the identification of new lines of research with the economic and legal area, it would be of interest to initiate a research program that studies what proportion of counterfeits are sanctioned, to which interest group the sanction is directed and if the sanction is proportional to the damage caused to society and the company. In addition, with regard to the study of counterfeit consumer behaviour, its development can provide information to guide the definition of public awareness strategies and help to adapt companies' marketing campaigns.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A world of counterfeits: Knowledge to decide

Marín‐Palacios,

Botey‐Fullat,

Márquez

2024

J of Consumer Behaviour

View full text Add to dashboard Cite

show abstract

“…While the ability to automatically distinguish between fake and genuine web shops has been well studied (e.g., [45,46]) and continues to be actively investigated ( [47][48][49]), the subsequent task of recognizing affiliate programs among the detected fake web shops has been less researched up until now, although it allows enforcement at scale and brings long-lasting results. One notable exception is [25], where the authors used a conventional clustering algorithm together with a few clustering features, mainly extracted from the HTML and the URLs of the websites.…”

Section: Description Of Experimental Scenariomentioning

confidence: 99%

Double-Constrained Consensus Clustering with Application to Online Anti-Counterfeiting

Carpineto,

Romano

2023

Applied Sciences

View full text Add to dashboard Cite

Semi-supervised consensus clustering is a promising strategy to compensate for the subjectivity of clustering and its sensitivity to design factors, with various techniques being recently proposed to integrate domain knowledge and multiple clustering partitions. In this article, we present a new approach that makes double use of domain knowledge, namely to build the initial partitions, as well as to combine them. In particular, we show how to model and integrate must-link and cannot-link constraints into the objective function of a generic consensus clustering (CC) framework that maximizes the similarity between the consensus partition and the input partitions, which have, in turn, been enriched with the same constraints. In addition, borrowing from the theory of functional dependencies, the integrated framework exploits the notions of deductive closure and minimal cover to take full advantage of the logical implication between constraints. Using standard UCI benchmarks, we found that the resulting algorithm, termed CCC double-constrained consensus clustering), was more effective than plain CC at combining base-constrained partitions, with an average performance improvement of 5.54%. We then argue that CCC is especially well-suited for profiling counterfeit e-commerce websites, as constraints can be acquired by leveraging specific domain features, and demonstrate its potential for detecting affiliate marketing programs. Taken together, our experiments suggest that CCC makes the process of clustering more robust and able to withstand changes in clustering algorithms, datasets, and features, with a remarkable improvement in average performance.

show abstract

“…Data availability and quality 8 (Baesens et al, 2021;Carta et al, 2019;Ileberi et al, 2022;Lucas et al, 2020;Sadaoui & Wang, 2017;Saia and Carta, 2019;J. Wang et al, 2020;Wei et al, 2013) 2 Imbalanced issue 4 (Baesens et al, 2021;Chang et al, 2022;Dastidar et al, 2022;Goswami et al, 2017) 3 Model drift 8 (Baesens et al, 2021;Chang et al, 2022;Gopal et al, 2022;Patil et al, 2018;Rezvani and Wang, 2022;Ruan et al, 2020;Sadaoui and Wang, 2017;Zhang et al, 2022) 4 Misclassification due to indetermincay 2 (Askari and Hussain, 2020;Dastidar et al, 2022) 5 Complication in data structure 1 (Dang et al, 2019) 6 Cost factors 3 (Chang et al, 2022;Ebrahim and Golpayegani, 2022;Kodate et al, 2020) Source: Processed by the Author These challenges have been identified based on their existence in relevant literature. In summary, the challenges relating to machine learning-powered e-commerce fraud detection include 8 frequencies of data availability and quality, 4 frequencies of addressing imbalanced datasets, 8 frequencies of combating model drift, 2 frequencies of dealing with misclassification due to indeterminacy, 1 frequency of managing complex data structures, and 3 frequencies of considering the financial implications of the fraud detection process.…”

Section: The Challenges Related To Machine Learning Powered E-commerc...mentioning

confidence: 99%

Machine Learning for E-Commerce Fraud Detection

Damayanti,

Adrianto

2023

JRABA

View full text Add to dashboard Cite

The study examines the effectiveness, challenges, and best machine learning algorithms for detecting e-commerce fraud. This study uses a systematic literature review to evaluate the effectiveness of machine learning-based e-commerce fraud detection, identify challenges, and identify the most effective techniques. The study examinedliterature extracted from the ScienceDirect, Emeralds, Wiley, and Springer databases, identifying 29 publications from recognized journals from 2012–2022, filtered using limitations and quality assessment criteria, and assessing paper eligibility. This study reveals that machine learning significantly enhances the accuracy of detecting e-commerce fraud. Yet, there are a number of issues that need to be resolved before machine learning can be utilized to detect e-commerce fraud. Poorer-quality data distribution is the biggest challenge in detecting e-commerce fraud. In order to determine the best machine learning strategy, the model's accuracy was also evaluated, and it was discovered that random forests performed the best in terms of accuracy. This study increases theoretical contributions as a continuation of previous research relevant to the concept of machine learning in detecting fraud in e-commerce. Then, based on the random forest's greater precision, it provides practical advice to e-commerce firms as a basis for decision-makers to find a suitable machine learning technique for fraud detection.

show abstract

Analysis of third-party request structures to detect fraudulent websites

Cited by 9 publications

References 42 publications

A world of counterfeits: Knowledge to decide

A world of counterfeits: Knowledge to decide

Double-Constrained Consensus Clustering with Application to Online Anti-Counterfeiting

Machine Learning for E-Commerce Fraud Detection

Contact Info

Product

Resources

About