Page 295 - Contributed Paper Session (CPS) - Volume 2
P. 295

CPS1863 La Gubu et al.
            0  are  the  risk  aversion  parameters,  namely  the  relative  measure  of  risk
            avoidance.
            The optimum solution to equation (1) with constraint of equation (2) is
                             1
                                                                      ′ −1
                                                   −1 ′ −1
                                                                            −1
                                             ′ −1
                      (, Σ) = (Σ −1  − Σ −1 ( Σ  )  Σ  ) + Σ −1 ( Σ  )         (3)
                             
            Equation (3) shows that the optimal portfolio (w) depends on inputs  and Σ.

            2.2 Clustering stocks
               Because the number of stocks available in the capital market is quite large,
            it is very difficult to determine the proportion of investment for each stock.
            Therefore, it is necessary to use data mining techniques to deal with this. One
            of the data mining techniques that can  be used is cluster analysis. Cluster
            analysis  is  a  statistical  analysis  that  aims  to  separate  objects  into  several
            groups that have the same/different characteristics from one group to another
            group.  In  this  analysis  each  group  is  homogeneous  between  members  in
            groups or variations of objects in groups that are formed as small as possible.
            Cluster analysis, also called segmentation, has various purposes. Everything is
            related to grouping or segmenting several objects into subsets or clusters.
            Objects in a cluster will have a closer relationship compared to objects in other
            clusters.
               There  are  many  cluster  techniques  in  the  literature.  In  this  study,  the
            hierarchy complete lingkage clustering technique will be applied. Hierarchical
            complete lingkage clustering technique is a clustering method based on the
            farthest  distance  between  objects.  If  two  objects  are  separated  by  long
            distances, then the two objects will be in one cluster, and so on.

            2.3 Sharpe ratio
               After the clusters are formed, then the performance of each stock will be
            assessed in each cluster using the Sharpe ratio. Sharpe ratio or Sharpe index
            is a measure of excess return (or risk premium) perunit risk in an asset. Sharpe
            ratio is used to characterize how well asset returns compensate investors for
            the risks taken. Sharpe ratio () is calculated by comparing the difference
            between  stock  returns  ()  and  risk  return  free  rate  ( )  with  a  standard
                                                                    
            deviation of stock return () or can be written as follows:
                       − 
                   =                                                     (4)
                         
               In general, it can be said that the greater the value of the Sharpe ratio of a
            stock, the better the performance of the stock.





                                                               284 | I S I   W S C   2 0 1 9
   290   291   292   293   294   295   296   297   298   299   300