The study presents an innovative approach aimed at amplifying student engagement with the Selfmade Ninja labs, utilizing a reward-centric framework that prioritizes user efficiency. This approach involves the meticulous calculation of various CPU metrics, encompassing elements such as CPU usage, memory usage, download and upload statistics, process identifiers, as well as read and write statistics. These metrics collectively offer a comprehensive view of user interactions within the platform. The gathered data is thoughtfully curated and stored in a JSON file, facilitating efficient data management and analysis. To facilitate the realization of this approach, a sophisticated machine-learning model is deployed. This model serves the pivotal purpose of predicting user efficiency, a crucial factor in determining the efficacy of their engagement with the Selfmade Ninja labs. Building upon this predictive prowess, a system of credits is established, intricately tied to a leaderboard that reflects individual user performances. Through this dynamic reward distribution mechanism, users are incentivized to actively participate and continually enhance their proficiency, thereby fostering a vibrant learning ecosystem. The culmination of this endeavour is a finely tuned predictive model that seamlessly allocates rewards to users based on their demonstrated engagement and proficiency. This tailored approach not only magnifies user motivation but also significantly augments the overall educational impact of the Selfmade Ninja platform. The integration of insights derived from both exploratory data analysis (EDA) and the predictive model ensures a holistic understanding of user behaviors and preferences. Consequently, the proposed reward-based system is elevated to a new level of efficacy, nurturing a learning environment where students are empowered to engage more meaningfully with the Selfmade Ninja labs, fostering enhanced learning outcomes.