Knowledge of the quality evolution of food products along the cold chain is of major importance to ensure safety and extend shelf-life. In order to study the evolution of food products, different sources of variability observed in practice such as food properties and product temperature in different links have to be considered. Different methods have been developed in the past to account, through modelling, for the variability of inputs on the output variance of a quality characteristic. The Monte-Carlo method, based on pseudo-random process, is the most widely used because of its simplicity and facility of implementation. The purpose of this study was to evaluate the product quality evolution along the cold chain considering both the variability of time temperature profiles and product initial quality (colour, microbial load, etc.) by means of the Monte Carlo method. Two methodologies based on global sensitivity analysis and an accept-and-reject algorithm was proposed to identify in an elegant way the most influencing factors on the final product quality.