This is the authors' abstract. We don't add key points for this paper.
Modern techniques have allowed for using advanced technology and tools in order detect fraud within an organisation. It is essential for any Banking sector or financial sector to identify those fraudulent activities that might be associated within their network. Different AI-based technology and ML algorithms are used within banking sectors of India and other countries of this world to determine frauds and unauthorised access. This research article have identified that Data mining is effective for the banking sector to target customers, who might develop fraudulent activities through the credit process. SVM, Logistic regression, Decision tree, Neural networks are used as data mining tools within banking sector’s fraud detection process, however all these tools required a data balancing method before structuring the model. Autoencoder is a model that is proposed for fraud detection without any data balancing. A secondary thematic data analysis process is developed within this research article to investigate of different variables relevant to this topic. It has been found that, proposed model for cyber-crime detection, AI-enabled automated fraud controlling system are effective to reduce risk within banking sector. Moreover, SAS is effective software used by banking sector to detect fraud. It generates alert signals for any fraudulent behaviour with system of banks. However, banking sectors need to engage good governance to mitigate challenge regarding lack of skill and expertise within their data mining process.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Biswas et al. (2022) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: