MBD: Bank Customer Propensity to Purchase Prediction Data

Twelve months of anonymized historical data on bank clients' transaction activity, dialog embeddings, and geo-activity. The dataset is designed to assist in predicting a customer's propensity to purchase various products within a month following a reporting date. It was created by ai-lab and last updated on Hugging Face in February 2025.

Use Cases

• Predicting customer product purchases based on historical transaction activity.
• Training models for targeted marketing campaigns using dialog embeddings.
• Analyzing customer geo-activity patterns to inform sales strategies.
• Developing and testing models with a reduced subset via the MBD-mini version.

Strengths

• Covers a 12-month period of historical customer data.
• Includes multiple data modalities: transaction activity, dialog embeddings, and geo-activity.
• Offers a reduced 'MBD-mini' version for faster development and prototyping.

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, file formats, and license information are unknown.

Provenance

Source

ai-lab on Hugging Face.

Collection Method

Likely collected from anonymized bank client records.

Time Range

Covers a 12-month historical period.

Freshness

Last updated 2025-02-25 12:06:32; freshness should be verified.