• Mohammed Shamail Farhan

Students placements are important at an educational institution, and they can affect the college's reputation. One of the most significant difficulties that higher education institutions confront today is improving student placement performance. When educational entities get more complex, placement prediction becomes more difficult. Educational institutions seek more efficient technology to aid in improved administration and decision-making procedures, as well as to help them develop new strategies. Providing new knowledge about innovative ideas to the management is one of the most effective approaches to solve the issues of enhancing quality. Knowledge may be derived from operational and historical data stored in the databases of educational organisations using machine learning techniques. The data set for system implementation includes student data from the past. These data are utilized to train the model for rule detection and classification, as well as to test the model. This method proposes a recommendation mechanism that forecasts the placement status of students. This strategy aids an organization's placement cell in identifying potential students, as well as paying attention to and improving their technical and interpersonal abilities. As a result, they will be able to put in more effort in order to get placed in higher-ranking companies. This method presents a suggestion mechanism for predicting students' placement status. For student placement prediction, data science techniques are used, and the system employs the most efficient algorithms, such as the "naive bayes algorithm" and the "KNN algorithm." Both algorithms are implemented in the C# programming language, and the results are compared, and the system determines which algorithm is the more efficient. Our system produced excellent results, with around 85% for the "naive bayes algorithm" and around 95% for the "KNN method." When compared to the naive bayes algorithm, the KNN approach produces better results.

Machine learning,Naive Bayes,KNN,Data Science,Placements,Supervised Learning

"A Real Time Application to Predict Student Placement Status", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 7, page no.c672-c681, July-2021, Available :http://www.jetir.org/papers/JETIR2107359.pdf

"A Real Time Application to Predict Student Placement Status", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 7, page no. ppc672-c681, July-2021, Available at : http://www.jetir.org/papers/JETIR2107359.pdf