Prediction models for Arabica coffee beverage quality based on aroma analyses and chemometrics

► Analyses of coffee volatiles are of great interest for quality control. ► Use of the chromatographic fingerprint of roasted coffees instead of peak areas is a significant innovation. ► Prediction of six sensorial attributes of Brazilian Arabica coffee quality. ► The results demonstrated that SPME-CG coupled with chemometrics is an effective technique for prediction of Arabica coffee quality.