In the realm of aviation, ensuring the optimal performance and safe operation of turbofan engines demands meticulous attention and proactive maintenance practices. The Remaining Useful Life (RUL) refers to the remaining time before a machine or its component requires repair or replacement. It serves as a critical measure in the field of predictive maintenance. Predictive maintenance involves scheduling maintenance based on predictions of equipment failure. By analyzing data measurements from the equipment, machine learning can be used to develop models that predict failure before it occurs. This paper presents a comparative study of machine learning algorithms for predicting the RUL of turbofan engines in aircraft. The study utilizes NASA Turbofan Simulation Dataset to construct the machine learning models. To enhance the accuracy of predicting maintenance requirements, this paper endeavors to employ several models and choose best among all. By thoroughly examining the performance metrics of various models and meticulously fine-tuning their parameters through random search, we aim to ascertain the Remaining Useful Life of the turbofan engine with unprecedented precision.