hedge strongfundstrong classification using k-means clustering method.pdf

9th International Conference on Computing in Economics and Finance, July 11-13, 2003, U of Washington, Seattle Hedge Fund Classification using K-means Clustering Method 1 Nandita Das Abstract Hedge fund databases vary as to the type of funds to include and in their classification scheme. Investment strategy and/or investment style are the basis for classification. Considerable variation is observed in the definitions, return calculation methodologies, and assumptions. There exists a myriad of classifications, some overlapping and some mutually exclusive. There is a need for an ‘alternative approach’ to hedge fund classification given the lack of ‘pure’ hedge fund types. The hedge fund literature shows an almost complete reliance on the existing hedge fund classifications. This means that research on hedge fund performance may produce different results based on the chosen database and the results are difficult to compare, as there are many different ways to classify any hedge fund. The varied classification of hedge funds probably attributes to the disparity in the numbers produced between different organizations measuring hedge fund performance. Asset class, region of investment, the trading strategy used, and the liquidity of the investment strategy can be the basis of hedge fund classification. This study uses cluster analysis approach to classify hedge funds. The classification is based on asset class, size of the hedge fund, incentive fee, risk- level, and liquidity of hedge funds. Nonhierarchical clustering method is used for the classification. The result is compared with the exi