Abstract State-of-the-art optical sorting systems suffer from delays between the particle detection and separation stage, during which the material movement is not accounted for. Commonly line scan cameras, using simple assumptions to predict the future particle movement, are employed. In this study, a novel prediction approach is presented, where an area scan camera records the particle movement over multiple time steps and a tracking algorithm is used to reconstruct the corresponding paths to determine the time and position at which the material reaches the separation stage. In order to assess the benefit of such a model at different operating parameters, an automated optical belt sorter is numerically modelled and coupled with the tracking procedure. The Discrete Element Method (DEM) is used to describe the particle–particle as well as particle–wall interactions, while the air nozzles required for deflecting undesired material fractions are described with Computational Fluid Dynamics (CFD). The accuracy of the employed numerical approach is ensured by comparing the separation results of a predefined sorting task with experimental investigations. The quality of the aforementioned prediction models is compared when utilizing different belt lengths, nozzle activation durations, particle types, sampling frequencies and detection windows. Results show that the numerical model of the optical belt sorter is able to accurately describe the sorting system and is suitable for detailed investigation of various operational parameters. The proposed tracking prediction model was found to be superior to the common line scan camera method in all investigated scenarios. Its advantage is especially profound when difficult sorting conditions, e.g. short conveyor belt lengths or uncooperative moving bulk solids, apply.