Abstract: Research on listed company comprehensive assessment has become an important focus problem for economists and investors.In this paper，the financial indexes reflecting the comprehensive capability of listed companies as main research objects including income per thigh，clean asset per thigh，profit rate of clean asset，Kohonen network with the advantage of clustering is applied to assess for listed companies.In order to improve the precision of solutions，a tabu-mapping method is also used to avoid the same output node to be mapped by more than one input in this paper.Experimental results show that Kohonen network is feasible and effective to assess listed companies，it can provide a new reference basis for government and investors，which has potential applications in the financial field.

Key words: Kohonen network, listed company, comprehensive assessment, tabu-mapping

摘要： 对上市公司综合评价的研究一直是国内外经济学家和投资者关注的焦点。以每股收益、每股净资产、净资产收益率等反映上市公司综合盈利能力的指标作为主要研究对象，利用Kohonen网络对上市公司进行聚类模拟，通过聚类的方法对上市公司进行综合评价。为了提高解的精度，还提出了禁忌映射的方法。实验结果表明，利用Kohonen网络对上市公司进行综合评价是可行的，得到了令人满意的结果。它为政府和投资者提供了一种新的参考依据，在金融领域具有较好的应用前景。

关键词: Kohonen网络, 上市公司, 综合评价, 禁忌映射