Student-Centric Explainable-AI Framework for Campus Placement Prediction

Placement drives are an important opportunity for the students. Yet many students find it difficult to understand their preparation level. Most of the existing models provide only result like placed or not, without giving an explanation. To address this gap ,this paper introduce an explainable AI-based system which predict the placement readiness score along with the impact of every factor on performance, and also give the actions for improvement. It also provides the student with a list of companies that he or she would be eligible for. This system uses different machine learning algorithms, to find a best fit model for predicting the placement. Student-related technical attributes and non-technical attributes are used as input features. The best performing model Random forest is selected of accuracy score 89.5 % .To increase the transparency, the system combines the shape, explainable AI technique to analyse the contribution of each feature.