Library Book Return Default Prediction Dataset with 10k Simulated Loans

10,000 simulated loan transactions from a university library system, intended for classification tasks. The data is synthetic and hosted on Kaggle, though specific creation details and update history are unknown. It is designed to model the risk of book returns being overdue or defaulted.

Use Cases

• Train a binary classifier to predict loan default based on simulated transaction features.
• Benchmark machine learning algorithms on a structured, synthetic financial transaction dataset.
• Study feature importance for default prediction in a controlled, library-specific lending environment.

Strengths

• Contains 10,000 records, providing a substantial sample for model training.
• Focuses on a specific, interpretable domain of library book lending.

Limitations

• Data is simulated, not real-world, which may limit generalizability to actual library systems.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

Kaggle

Collection Method

Simulated/generated