Analysis of the cryptocurrency market using different prototype-based clustering techniques

Abstract Since the emergence of Bitcoin, cryptocurrencies have grown significantly, not only in terms capitalization but also number. Consequently, cryptocurrency market can be a conducive arena for investors, as it offers many opportunities. However, is difficult to understand. This study aims describe, summarize, and segment main trends entire 2018, using data analysis tools. Accordingly, we propose new clustering-based methodology that provides complementary views financial behavior cryptocurrencies, one looks associations between clustering results, other factors are involved clustering. Particularly, involves applying three different partitional algorithms, where each them use representation namely, yearly mean, standard deviation returns, distribution returns been applied markets previously, time series returns. Because outlook market, examine integration obtain fine-grained market. In conclusion, analyze association results with descriptive features including age, technological attributes, ratios derived from them. will help enhance profiling clusters additional insights, find variables. this describes whole based on graphical information, scalable reproduced by investors who want understand quickly, those look performance.In our 2018 2019 extended period, found typically segmented few (five or less), even considering intersections, 6 more populations account 75% Regarding features, some volume, capitalization, ratios, which could explored future research.