Skip to main content

Table 2 Comparison of statistical measures of the performance of the median-based machine learning consensus predictor and the median-based human consensus predictor in terms of the root mean squared error (RMSE), coefficient of determination—which is the square of the Pearson correlation coefficient (R2), Spearman rank correlation coefficient (ρ), number of correct predictions within a margin of one log S unit (NC), and average absolute error (AAE)

From: Can human experts predict solubility better than computers?

  Median-based ML Median-based human
RMSE 1.140 1.087
R2 0.601 0.632
ρ 0.762 0.817
NC 18 21
AAE 0.778 0.732