Skip to content

Dataset · mteb

Online banking customer query classification

mteb/banking77

A text benchmark from the MTEB ecosystem for intent classification of customer bank inquiries.

What's inside

The dataset contains 10k to 100k English text queries from the online banking domain, labeled with corresponding user intents. The set is adapted for the MTEB (Massive Text Embedding Benchmark) framework for text classification.

What you can do with it

  • Evaluating text embedding quality in the standard MTEB benchmark
  • Training and testing intent classifiers for banking chatbots and support services
  • Fine-tuning compact language models for customer inquiry routing
Tasks
Text classification
Languages
English
Size
10K–100K rows
Downloads this month
22.8K
Likes
23

Models trained on it

How to load it

from datasets import load_dataset

ds = load_dataset("mteb/banking77")