Abstract: Credit card fraud is the most serious problem in today's world, and there is an urgent need to combat it. "Credit card fraud is the process of cleaning dirty money, making the source of funds untraceable." On a daily basis, huge amounts of money are exchanged in the global market, making detecting credit card fraud activity a difficult task. As previously stated, (Anti-credit card fraud Suite) is introduced to detect suspicious activities, but it is only applicable to individual transactions and not to other bank account transactions. To address these issues, we propose a machine learning method based on 'Structural Similarity.' This method identifies common attributes and behaviour with other bank account transactions. It is difficult to detect credit card fraud transactions from large datasets, so we propose case reduction methods to reduce the input dataset and then find pairs of transactions with other bank accounts that share common attributes and behaviour.
Keywords: Machine learning ,SVM algorithm
Copyright Form