Summary Predicting carbon and oil prices is recently gaining relevance in the climate change literature. This is due to the fact that conventional energy market analysis and the design of mechanisms for climate change mitigation constitute key variables for artificial carbon markets. Yet, modelling non‐linear effects in time series remains a major challenge for carbon and oil price forecasting. Hence, hybrid models seem to be appealing alternatives for this purpose. This study evaluates the performance of 12 hybrid models, which weigh results from random forest, support vector machine, autoregressive integrated moving average and the non‐linear autoregressive neural network models. The weights are determined by (i) assuming equal weights, ( ii) using a neural network to optimise individual weights and (iii) employing deep learning techniques. The findings of our work confirm the salient characteristics of modelling the non‐linear effects of time series and the potential of hybrid models based on neural networks and deep learning in predicting carbon and oil price returns. Furthermore, the best results are obtained from hybrid models that combine machine learning and traditional econometric techniques as inputs, which capture the linear and non‐linear effects of time series.