• MUTHU DAYALAN

Machine learning relies on the technique of identification of the influential cause-and-effect relationship, for making accurate future prediction. It involves the application of artificial intelligence to enable the computer learn without subjection to artificial programming. Machine learning is an effective technique for improving risk management through enhanced detection of the frauds and compliance of control violations. The machine-learning model applies accumulated historic data to pinpoint the fraudulent transactions. The strengths, which makes machine learning an effective fraud detector, include facilitating real time decision-making, improved accuracy and a rapid response to change. The assembles used for detecting fraud include regression analysis, artificial neutral networks, and decision trees.

machine learning, fraud detection, model, prediction, pattern recognition

"Adaptive Fraud Detection through Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.4, Issue 9, page no.328-331, September-2017, Available :http://www.jetir.org/papers/JETIR1709053.pdf

"Adaptive Fraud Detection through Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.4, Issue 9, page no. pp328-331, September-2017, Available at : http://www.jetir.org/papers/JETIR1709053.pdf