EEG-based pain assessment methods has been widely accepted in recent years. However, performance of cross-individual prediction degraded considerably due to the substantial inter-individual variability in pain-evoked EEG responses. This study aims to improve the accuracy of cross-individual pain prediction via reducing the inter-individual variability. Motivated by our finding that an individual's pain-evoked EEG responses is significantly correlated with his/her spontaneous EEG in terms of magnitude, we proposed a normalization method for pain-evoked EEG responses using one's spontaneous EEG to reduce the inter-individual variability. Continuous prediction for pain trials using spontaneous-EEG-normalized magnitudes of evoked EEG responses as features was developed. Results show that the proposed normalization strategy can effectively reduce the inter-individual variability in pain-evoked responses and lead to a higher prediction accuracy.