One of the most important applications of chemoinformaticsChemoinformatics involves studying the relationship between a molecule’s properties and its structural characteristics. Therefore, the key to unlocking a molecule’s function and properties lies in understanding its molecular structure. Choosing appropriate molecular descriptors with good dependence on the specific property is crucial. Various statistical methods, including genetic algorithmsGenetic algorithms (GA), artificial neural networks, multiple linear regressions, partial least squares regression, or modern machine learning tools such as XGBoost, support vector machine, and genetic function approximation are employed to investigate the significant relationship between structure and property. Due to the hazards and risks involved in the field of energetic materialsEnergetic materials, these modeling methods have been widely used to predict a wide range of properties, including physiochemical properties, energetic properties, or sensitivity parametersSensitivity parameters. In recent years, there have been reports on the use of predictive models as tools for virtual screening to design and theoretically evaluate new energetic materials. In the present chapter, the aim is to provide an overview of the various applications of QSPR modeling in energetic materials.