Explainable Student Grade Prediction Paper

I am seeking an experienced academic researcher to deliver a complete, journal-ready research paper on Explainable AI (XAI) for predicting and interpreting student academic performance.

The study must use multiple academic data sources (exams & quizzes, assignments & projects, and class participation records), which I will provide in CSV format.

Scope of work:
• Clean, preprocess, and align datasets using student IDs and time frames
• Perform relevant feature engineering
• Build at least one strong predictive model (with optional comparisons)
• Apply explainability techniques such as SHAP, LIME, decision trees, or equivalent, with clear justification
• Evaluate predictive performance and interpretability
• Produce publication-quality visualizations highlighting influential features
• Write the full research paper (Abstract, Introduction, Related Work, Methodology, Results, Discussion, Conclusion, References) in IEEE or Springer format
• Provide fully annotated Python or R notebooks to reproduce all results, figures, and tables

Deliverables:
• Cleaned dataset
• Complete manuscript (submission-ready)
• Reproducible code/notebooks and figures

Milestones:
1. Cleaned dataset + baseline model results
2. Final manuscript + complete codebase

Requirements:
• Prior experience publishing academic papers
• Strong background in Explainable AI / Machine Learning
• Familiarity with educational or student performance data preferred