The article is a review of the potential of machine learning (ML) to explore how monetary policy is transmitted in the scenario in which the dominance of digital payments in the economy is experienced. As the cash-based systems are substituted with digital transactions, the formal policy tools such as interest rates and reserve requirements are introduced to the financial markets and households in nonlinear terms. Such dynamics are not usually represented by the traditional forms of econometric models which are predetermined by the linearity and inertia assumption. The high-frequency data on the transactions may be simulated to determine the consumer behavioral pattern and the flow of the digital credits, which, in its turn, may be simulated with the help of the ML methods (neural networks, random forests, and natural language processing). The paper shall discuss how the practices have played a significant role in the realization of the dynamics of channel of transmission of monetary transactions in the digital economies under the context of the interest rate pass-through, credit supply and dynamic of inflation. These findings suggest that the interpretation with the help of MLs is more important in terms of predictive power and is also described with dynamic interdependence between the utilisation of digital payments, monetary shocks and real economic performance. Such lessons will also help streamline the central bank policymaking process, particularly in the growing markets where digital finance has surpassed the conventional banking infrastructures. It is also mentioned in the paper that AI-empowered applications are of importance to improve the monetary policy in accordance with sustainable growth and technological innovations, which are directly linked to SDG 8 (Decent Work and Economic Growth) and SDG 9 (Industry, Innovation and Infrastructure).