Solvent-aided thermal stimulation supplies a small quantity of hydrocarbon solvent to the injected steam to improve thermal recovery in oil sands reservoir. Injection pressure is one key control parameter, which determines the amount of solvent and steam mixture consumed and its optimum level dominates the economic efficiency of thermal method. The paper depicts the optimal strategy of operating pressures to achieve the maximum economic value, the scheme of which is based on artificial neural network (ANN). The multi-layer perceptron using backpropagation minimizes the objective value including bitumen production, steam injection, solvent retention, commodity price, and manufacturing cost. The numerical approach integrating with ANN shows accurate predictability similar to the time-consuming reservoir simulation. The application to the Athabasca oil sands reservoir confirms the enhanced results compared with constant injection scenario and proposes the optimal schedule of injection pressures that repeats the increment and the decrement until reaching the same pressure level between injection and production well. It maintains consistency of peak production rate on account of latent heat despite decreasing cycle amplitude. The developed model could be applicable to make up injection scenarios economically without any modification of production facilities.