In this study, the price dynamics of Certified Emission Reductions were forecasted by comparing and acquiring the most consistent and accurate forecast model using the diffusion processes: Geometric Brownian Motion, Vasicek Model and Mean Square Root Process. The assumption of each model with drift and diffusion component were investigated focusing on the Certified Emission Reductions prices traded within European Energy Exchange (EEX) between the years of 2012-2020.The forecasted prices were compared to the actual to evaluate the validity of the models. Based on the research findings, Bayesian information criterion, which determined the goodness of fit to assess the performance of the model with respect to how well it explains the data, shows that vasicek model is the most preferred model among the three models since it has the lowest Bayesian information criterion (BIC). This study compared the accuracy of the models, Geometric Brownian Motion, Vasicek Model and Mean Square Root Process, in terms of forecasting the price dynamics of CERs, and concluded the vasicek most is the most accurate among the three models since the predictive power is high toward a specified time frame proven by the lower value of mean absolute error and Mean Absolute Percentage Error.