INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
The frequency of fraudulent operations presents a serious peril to the security and integrity of digital fiscal systems, given the explosive increase of online deals. This study presents a new strategy to reduce online sale fraud by putting in place a strong fraud discovery system that makes use of machine literacy methods.Using slice- edge machine literacy ways, the suggested system models and analyzes sale data to make real- time distinctions between fraudulent and authentic deals. By rooting material information from a variety of sale attributes, point engineering and selection approaches are used to ameliorate the system's capacity to identify aberrantbehavior.In order to duly train the model, a large dataset with a variety of sale situations is named, guaranteeing that the system can acclimate to changing fraud trends. To determine which supervised literacy system is stylish for accurate fraud discovery, a variety of models are delved and varied, including decision trees, support vector machines, and neural networks.The system uses unsupervised literacy styles in addition to supervised literacy to identify new fraud patterns in the absence of labeled training data. The system can acclimate to new and unlooked-for fraud cases thanks to clustering algorithms and anomaly discovery techniques.Extensive tests are carried out using real- world sale datasets to validate the utility of the proposed system, and performance measures including perfection, recall, and F1 score are used to estimate the delicacy and responsibility of the system. The issues show how well the system can identify fraudulent deals while reducing false cons, which improves overall sale security.The study's findings offer perceptive information about the use of machine literacy in the field of detecting online sale fraud, giving fiscal institutions and other businesses a useful tool to secure their digital deals and safeguard the interests of stakeholders and guests. This study adds to the continuing sweats to develop robust and flexible results that can offset online fraud's dynamic character in the fleetly changing digital geography.
Keywords:
Cite Article:
"Advanced Online Transactions Fraud Detection Using Machine Learning", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.9, Issue 3, page no.b511-b513, March-2024, Available :http://www.ijnrd.org/papers/IJNRD2403155.pdf
Downloads:
00056
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn