This project is an examination of factors that impact programming aptitudes. It examines the advancement of machine learning models to anticipate approaching students' performance. Our variables anticipate whether students will be strong or weak developers with 60 to 70% precision. Students find computer programming problematic and fight to pro the focus thoughts. Recognizing students who face difficulties in programming, is inconvenient and habitually educators don't have the thought about how well students get along until after the main examination. This examination may not occur until a couple of months after the module has started and whether or not the assessment is expressive of likely overall execution on the module, it may be passed the final turning point for students to pull back from the course or for educators to intervene to continue students from missing the mark. The factors investigated often as possible depending upon the students being involved with the module material and consequently, it is difficult to tell how farsighted comparative components would be at whatever point assessed before on the module. A model that could anticipate likely programming execution in the underlying stages and help with diminishing this issue isrecommendable.