Applications of SOM2W Network for Stock Companies Comprehensive Assessment

An improved model based on Kohonen neural network, called self-organizing map neural network with two winners (SOM2W), is applied to assess stock companies in this paper. In addition, in order to improve the precision of solutions, tabu-mapping method is also used to avoid that the same output node is mapped by more than one input. The clustering analysis for the stock is also done by using SOM2W neural network in this paper. The financial indexes reflecting the comprehensive capability of stock company as main research objects including income per thigh, clean asset per thigh, profit rate of clean asset. Experimental results show that SOM2W network is feasible and effective to assess and select stocks, it could provide a new reference basis for government and investors, which has potential applications in the financial field.