Response Surface Methodology (RSM) is a statistical method to design experiments and optimize the effect of process variables. RSM is based on the principles of design of experiments or DOE. Design of experiments or DOE is a field of applied statistics that plans, conducts, analyses, and interprets controlled tests to assess factors that affect parameter values. Response surface methodology or RSM uses a statistical method for designing experiments and optimization. Despite the potential of response surface methodology to predict and optimize engine performance and emissions characteristics, a comprehensive review on RSM for biofuels, particularly for internal combustion engines (ICEs), is difficult to find. The review of response surface methodology is sometimes included together with other machine learning approaches such as ANN. Therefore, a review article that is exclusively written to address the specific of RSM for biofuel and ICE is required. This review article offers a fresh perspective on the application of RSM for biofuel in ICE. This article aims to critically review the RSM to optimize engine performance and emissions using biofuel. The study concludes with several possible research gaps for future works of RSM biofuel application. Although response surface methodology or RSM has drawbacks such as extrapolation inaccuracy outside the investigational ranges and discrete variables error, RSM has numerous advantages to design, model, estimate, and optimize biofuel for ICE with satisfactory accuracy. With its prediction and optimization capability, response surface methodology has the potential to assist the development of ICE optimization powered by biofuel for sustainability energy transition. © 2023 The Authors