Faced with current energetic and environmental concerns, the development of safer and cleaner products is a great challenge for industry and a priority at R&D level. It concerns a large diversity of chemicals and applications and encourages innovations in products, in raw materials, and in the involved processes. Complementary to experimental means, INERIS developed Quantitative Structure-Property Relationship models (QSPR) for the prediction of physico-chemical properties of various families of chemicals like amines, organic peroxides, ionic liquids or surfactants. QSPR models are predictive methods based on correlations between the molecular structures of chemicals and their macroscopic properties. Such methods have been up to now mainly devoted to biological, toxicological applications but their use to predict physico-chemical properties is of growing interest in recent years [1]. In addition, quantum chemical tools are used not only to compute relevant molecular descriptors (notably issued from the Conceptual Density Functional Theory) but also to evidence the underlying chemical mechanisms. The development of such models is notably recommended, in the framework of the European REACH regulation, as an alternative to experimental tests for reasons. So, models are derived according to the OECD validation procedures [2] in view of being submitted to the EU Joint Research Center (JRC) for acceptance or to existing tools (like OECD/ECHA QSAR toolbox [3]) for integration. Such methods also represent pertinent tools in screening procedures to select the best performances in any functional properties (e.g. in chemical process) or ensuring at best against hazardous properties (like flammability or explosive properties) for the development of safer products (safety-by-design) or for substitution purpose. In this presentation, we propose to exemplify some key obtained models and we discuss how such models will help in the development of safe green chemicals.