3D Subspace Clustering for Value Investing
Kelvin Sim, Vivekanand Gopalkrishnan, Clifton Phua, Gao Cong · IEEE Intelligent Systems · 2012
Using Graham's rules on picking stocks has been proven to generate profits for value investors. The authors propose using 3D subspace clustering to generate rules to pick potential undervalued stocks; 3D subspace clustering is effective in handling high-dimensional financial data and is adaptive to new data. In addition, its results aren't influenced by human biases and emotions, and are easily interpretable.