This work addresses the industrial process of compounding automotive gasoline by a controlled blending of feedstock hydrocarbon streams deriving from different stages of the cracking and refining process of naphtha. In this process, gasoline quality and profitability are directly affected by both the composition of each stream and the ratio of the streams to each other in the gasoline. Indeed, factors such as the process conditions, feedstock supply, production costs and origin of the naphtha frequently vary in both composition and ratio. As a result, the gasoline blending recipes must change constantly over time to keep up with the quality and economic characteristics of the product, with octane rating as a critical operational parameter in these processes. Near Infrared (NIR) spectroscopy is able to detect changes in composition and it can be considered during the design of a gasoline. Moreover, the use of NIR spectroscopy makes it possible to reduce significantly the time needed for analyzing the parameters of interest in the process, compared to the analytical methods that are commonly used. The main purpose of this work was to develop an off-line simulator of octane number in automotive gasoline based on NIR spectroscopy and chemometrics, aiming to improve the compounding process. The simulator was developed on the basis of the mathematical reproduction of gasoline spectra by a virtual controlled mixture of the near infrared (NIR) spectra of the hydrocarbon streams at appropriate ratio. Spectra were recorded with two instruments, a benchtop FT-NIR and a handheld instrument. Partial Least Squares (PLS) regression models were developed and validated to estimate the octane number from the simulated NIR spectra for potential gasolines. The comparison among the octane number predictions from the simulated spectra, the real NIR spectra and, also, the reference values, at different times over 2 years of production, representing a critical step in the development of the simulator, showed that the simulated spectra were able to predict values reliably. The developed octane simulator has an excellent potential for improving efficiency in the compounding process of automotive gasoline.