This study investigated the co-pyrolysis of waste polyethylene (WPE) and polystyrene (WPS) for oil production under different operating conditions (temperature and carrier gas flow rate). The ratio of the real-life WPE and WPS is different in different regions. Therefore, the interactions of operating conditions were investigated under different WPE/WPS mixture compositions. A hybrid model of artificial neural network-genetic algorithm (ANN-GA) was adopted to predict and optimize the co-pyrolysis oil yield due to the complex interactions of the WPE/WPS mixture composition and operating conditions. Consequently, the highest oil yield was 82.33 wt% under 525°C, 10 wt% PS, and a non-sweeping atmosphere (0 mL/min). The results indicated that high temperature, low PS mass fraction, and low carrier gas flow rate led to a higher oil yield. The WPE/WPS co-pyrolysis oils were composed of alkanes, alkenes, and aromatics. Meanwhile, styrene accounted for the highest proportion of aromatics in oils. ANN-GA was also adopted to predict and optimize the oil components and fractions. The results revealed that low temperature, high PS mass fraction, and low carrier gas flow rate were conducive to a light WPE/WPS co-pyrolysis oil production. The findings could guide the industrial process of waste plastic pyrolysis in different regions. Moreover, ANN-GA coupled with central-composite design can be used to regulate different target products under more complex conditions due to its good robustness.