Machine learning and big data: Supporting decision making on fraud detection

Healthcare and medical insurance are vulnerable areas for health care fraud. Traditional fraud detection efforts were unable to cope with the rapidly increasing health care utilisation and costs. A machine-learning tool is needed to detect potential fraud more effectively and efficiently.

As of 31 December 2020, this good practice found 30,000 cases of potential fraud with a total savings of 603.73 billion of Indonesian rupiah (IDR) or 41.93 million US dollars (USD). Machine learning can detect potential fraud faster and more efficiently, which reduces detection time, predicts more accurately using large datasets, and provides cost-effective solution.