A statistical learning approach for stock selection in the Chinese stock market

Financial Innovation

Table 6 Feature importance scores in different time periods

Factors	2003–2004	2005–2006	2007–2008	2009–2010	2011–2012	2013–2014	2015–2016	2003–2016
R1	0.71	1.00	1.00	0.96	0.50	1.00	1.00	0.88
R2	1.00	1.00	1.00	0.46	1.00	0.88	0.46	0.83
R3	0.75	0.96	0.50	0.17	0.08	0.58	1.00	0.58
R4	0.67	0.63	0.46	0.29	0.17	0.04	0.38	0.38
R5	1.00	1.00	0.50	0.21	0.46	0.67	0.67	0.64
R6	0.58	1.00	0.54	0.33	0.54	0.92	0.83	0.68
R7	0.25	0.63	0.92	0.42	0.00	0.21	0.67	0.44
R8	0.08	0.42	0.00	0.13	0.13	0.00	0.42	0.17
R9	0.92	0.88	0.67	0.67	0.04	0.13	0.42	0.53
R10	0.17	0.75	0.54	0.00	0.46	0.71	0.17	0.40
R11	0.54	0.54	0.17	0.83	0.75	0.33	0.63	0.54
R12	1.00	1.00	0.79	0.29	0.13	0.21	0.92	0.62
SD	0.79	0.46	0.42	0.33	0.54	0.79	0.83	0.60
Skew	0.50	0.50	0.38	1.00	0.92	1.00	0.50	0.68
Kurt	0.54	1.00	0.50	0.88	0.79	0.54	0.96	0.74
Sharpe	0.13	0.58	0.00	0.42	0.13	0.83	0.50	0.37
Alpha	0.42	0.83	0.04	0.17	0.54	0.25	0.58	0.40
Beta	0.13	0.33	0.38	0.13	0.50	0.96	0.33	0.39
Corr	0.75	0.79	0.21	0.58	0.58	0.33	0.67	0.56
Vol	0.58	0.79	0.25	0.83	0.42	0.79	0.79	0.64
DD	0.71	0.38	0.46	0.58	0.42	0.08	0.13	0.39
Average FI	0.58	0.74	0.46	0.46	0.43	0.54	0.61	0.55