Medical Claim Fraud Analysis Disclosure Trends in Cyber Security using Machine Learning Techniques

Abstract

Complex Big Data systems in modern organization are gradually becoming targeted by existing and emerging
new threat agents. Intricate and specialized attacks will increasingly be used to enslave vulnerabilities and weaknesses. With
the ever-increasing trend of cybercrime incidents happening due to these vulnerabilities, the effective vulnerability
management is imperative for the modern organizations regardless of their size. However, organizations struggle to manage
the sheer volume of vulnerabilities discovered on their networks. Moreover, vulnerability management tends to be more
reactive in practice. Attentive statistical models, simulating anticipated volume and dependence of vulnerability disclosures,
will undoubtedly provide important perception to organizations and help them become more protective in the management of
cyber risks. By influencing the rich yet complex historical vulnerability data, our proposed work and conscientious
framework has enabled this new capability. By utilizing this sound framework, we initiated an important study on not only
handling unrelenting volatilities in the data but also further unveiling multivariate dependence structure among the different
vulnerability risks. In sharp contrast to the existing studies on invariant time series, we consider the more general
multivariate case striving to capture their intriguing relationships. Through our extensive empirical studies using the real
world vulnerability data, we have shown that a composite model can effectively capture and preserve long-term dependency
between different vulnerability and exploit disclosures. In addition, this work gives the way for further study on the random
perspective of vulnerability proliferation towards building more accurate measures for better cyber risk management as a
whole