Table 4: Results for housing data; the number of clusters is set to 4, ; κ is the ratio of the number of selected data versus the number of selected features.

FeatureData = 10%Data = 20%Data = 30%Data = 40%Data = 50%Data = 60%Data = 70%Data = 80%Data = 90%Data = 100%
(# of data = 51) (# of data = 101) (# of data = 152)(# of data = 202)(# of data = 253)(# of data = 304)(# of data = 354)(# of data = 405) (# of data = 455) (# of data = 506)
RMSE RMSE RMSE RMSE RMSE RMSE RMSE RMSE RMSE RMSE

10%51.0 101.0 152.0 202.0 253.0 304 354.0 405.0 455.06.655 ± 0.0615067.437 ± 0
20%17.0 33.7 50.7 67.3 84.3 101 118.0 135.0 151.75.149 ± 0.0711695.039 ± 0.096
30%12.8 25.3 38.0 50.5 63.3 76 88.5 101.3 113.84.536 ± 0.0261274.578 ± 0.01
40%10.2 20.2 30.4 40.4 50.6 60.8 70.8 81.0 91.04.343 ± 0.0261014.233 ± 0.079
50%7.3 14.4 21.7 28.9 36.1 43.4 50.6 57.9 65.04.077 ± 0.09272.34.005 ± 0.082
60%6.4 12.6 19.0 25.3 31.6 38 44.3 50.6 56.93.931 ± 0.10263.33.803 ± 0.088
70%5.7 11.2 16.9 22.4 28.1 33.8 39.3 45.0 50.63.799 ± 0.04156.23.668 ± 0.043
80%5.1 10.1 15.2 20.2 25.3 30.4 35.4 40.5 45.53.645 ± 0.06550.63.526 ± 0.049
90%4.3 8.4 12.7 16.8 21.1 25.3 29.5 33.8 37.9 42.2
100%3.9 7.8 11.7 15.5 19.5 23.4 27.2 31.2 35.0 38.9