The quantitative structure-retention relationship (QSRR) is a significant approach in chromatography and is used to predict the retention time of unknown compounds. In the present research article, the QSRR approach is employed to develop robust models of 1176 flavor and fragrance compounds on the OV-101 glass capillary gas chromatography column using a statistical parameter “correlation intensity index (CII)”. This CII parameter is featured in the most recent release of the CORAL programme (www.insilico.eu/coral). The optimal descriptor i.e. descriptor of correlation weight (DCW) computed by simplified molecular input-line entry system (SMILES) notation is employed to build QSRR models. Two target functions, TF1 (WCII=0) and TF2 (WCII=0.3) are applied to design 12 QSRR models from six splits using the balance of correlation strategy. The models created using CII are better in terms of statistical results. The numerical value of Rvalidation2=0.9561 of TF2Split1 is found to be considerably greater than that of the Rvalidation2 of the other splits of both target functions, hence, it is acknowledged as a leading model. The lists of structural attributes responsible for the changes in the retention index (RI) of flavors and fragrances compounds are also retrieved and discussed. Finally, a consensus model is built utilising the allocation structure of split 1 and the modified consensus (CM1) i.e. an average of predictions from all 'qualified' Individual models is found best model based on MAE (95%; test). The numerical value of the determination coefficient (R2) of the test set for the modified consensus (CM1) model is found 0.9772 which is higher than the leading Model.