Historical Data-Driven Placement Analysis Using Explainable Artificial Intelligence

In recent years, securing suitable employment has been a challenging task without proper knowledge and skills. Traditional methods of educational institutions, which involve manual data analysis, basic statistical tools, and implicit subjective judgment, often cannot capture the nuances that go into student employability. The system aims to address the challenge of improving placement outcomes for students in a labour market that has grown increasingly competitive. The system will be analysing past placement records, establishes the key trends and patterns contributing to successful placements through the application of Explainable Artificial Intelligence (XAI) techniques. The process starts by data collection and preprocessing of the data of student placements over the previous years. Descriptive data analysis is conducted to find relationships and trends in the dataset between the variables, detailing the performance of students. The dataset is then trained using multiple models and the highest accuracy algorithm are used for the prediction. Applying explainable artificial intelligence techniques (SHAP) to the highest accuracy model would produce transparent outcomes, providing a clearer understanding and also provide which features are important for the placements. Thus, understanding the essential components would help educational institutions to expand placement numbers by identifying broader opportunities and formulate strategies for student employability.