To determine the sensitivity of density of the data set we carried out
an experiment where we varied the value of *x* from 0.2 to 0.9 in
an increment of 0.1. For each of these train/test ratio values we
ran our experiments using the two prediction generation
techniques-basic weighted sum and regression based approach. Our
results are shown in Figure 5. We observe that the quality of
prediction increase as we increase *x*. The regression-based approach
shows better results than the basic scheme for low values of *x* but
as we increase *x* the quality tends to fall below the basic
scheme. From the curves, we select *x*=0.8 as an optimum value for our
subsequent experiments.