jiegzhan/multi-class-text-classification-cnn

Classify Kaggle Consumer Finance Complaints into 11 classes. Build the model with CNN (Convolutional Neural Network) and Word Embeddings on Tensorflow.

44
/ 100
Emerging

Implements 1D convolution filters over word embedding sequences to capture n-gram patterns in complaint narratives, with configurable hyperparameters via JSON. Provides separate training and inference pipelines—`train.py` learns embeddings and CNN filters end-to-end, while `predict.py` loads checkpoints for batch classification on new complaints. Built entirely on TensorFlow with support for compressed CSV input data.

426 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 25 / 25

How are scores calculated?

Stars

426

Forks

195

Language

Python

License

Apache-2.0

Last pushed

Mar 25, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/jiegzhan/multi-class-text-classification-cnn"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.