Market Research Classification Model

I have a sizeable market-research dataset and I need a full classification pipeline built around it. The job starts with exploring and cleaning the raw survey responses, moves through feature engineering, and finishes with a well-tuned model that can reliably assign each record to the correct category. I would like you to: • Perform exploratory analysis to spot anomalies and guide preprocessing. • Build several candidate classifiers (e.g., logistic regression, random forest, gradient boosting, or any modern alternative you find suitable), compare them with cross-validation, and select the best. • Document the whole process in a clear, reproducible Jupyter notebook (Python, pandas, scikit-learn, or comparable libraries). • Deliver the final trained model, the notebook, and a concise report highlighting key metrics (accuracy, precision-recall, confusion matrix) so I can judge real-world performance. A clean codebase, thoughtful comments, and explanation of any assumptions you make will be part of the acceptance criteria.

Project ID: 40569791