In silico methods is a cost- and time-effective way to synthesize materials. Refractive index (n) is an important characteristic of an optical material. This work contains a quantitative structure–property relationship (QSPR) model that was developed to predict the (n) of 262 polymers collected from various sources. Several models were created, where a four-variable model showed the best predictive performance. The best model’s predictability was validated using the leave-one-out technique, external set, and y-scrambling methods. For (n), ionization potential, polarizability, 2D and 3D geometrical descriptors were the most influential. The model can be used to predict (n) for untested polymers.