The objective of this paper is predicting the production of electrical power from human movements by the utilization of piezoelectric materials. The piezoelectric sensor creates electricity by applying mechanical pressure or vibration to the sensor along with movements like walking and running. The machine converts the mechanical energy present in the motion to electrical energy, which can be tapped and utilized to power small electronic devices such as LEDs, sensors, and wireless modules. Besides the power production function, machine learning is applied at a rudimentary level to investigate human movements and pressure. Based on the information, the power production can be estimated and the efficiencies enhanced. The integration of rudimentary machine learning and piezoelectric power harvesting is therefore a clean, green, and feasible means for tapping power from day-to-day human activities.