Risk measures-based cluster methods for finance

This paper performs an extensive comparison of cluster techniques for financial applications based on risk measures and returns as classification variables. We consider the largely used in literature. For analysis, we use a database composed daily U.S. equity market. As applications, capital determination, portfolio optimization, asset pricing. found that number clusters varies over years. The years with fewest coincide periods instability, such 2008 (Subprime Crisis) 2015 (slowdown United States domestic product). Overall, observe our data support superiority Fanny MC approaches. By construction, both are more robust to distinct probabilistic distribution data, which is typically case data. Furthermore, results highlight practical utility considering variables applications.