Plastic waste is becoming more and more abundant in typical Municipal Solid Waste (MSW). Though recycling would be the optimal solution for plastic waste disposal, these techniques can recycle a limited amount of the overall plastic waste produced, for this reason energy recovery technologies are receiving more attention for the treatment and reuse of plastics aimed at the production of usable fuels for energy production or raw materials for petrochemical industry. Among these technologies, catalytic pyrolysis is a promising technique that can be used in order to avoid typical problems occurring with thermal pyrolysis (e.g. breaking long polymer structures and reducing energy consumption of the process). Even if large efforts are currently made in order to understand the factors influencing catalytic pyrolysis, some of the existing models showed limited applicability in real plants especially because of large deviations from controlled experimental conditions under which they have been derived. In current study, time series modeling of catalytic pyrolysis of plastic wastes has been investigated employing two distinctive multivariate modeling methods namely, Least Square Support Vector Machine (LS-SVM) and Artificial Neural Network (ANN). Sufficient experimental data sets from three synthesized sample types were utilized to form both LS-SVM and ANN models effectively. After proper training of both models, an unseen test data set of each sample type was applied to measure the predicting performance of developed models. In both training and prediction sections, accuracy of both models was analyzed using two statistical error measuring methods namely, the Mean Squared Error (MSE) and the coefficient of determination (R^2). Analysis of obtained outcomes from training and prediction parts revealed that both ANN and LS-SVM methods are quite reliable and precise tools for time series modeling of pyrolysis process.