Skip to main content

Use wide and deep model to do multi-classification tasks.

Project description


Use wide and deep model to do multi-classification tasks.

This model is developed for the debt-collection robot. The robot calls customers within several topics. However, the human agents make different performances in these topics based on the payback money. If we find in a subtopic, human agents make a better performance, we will analyze the conversations they make with customers and write specific strategies for robots.

We collect the conversation between robot and customers and transform them into word2vector using a pre-trained model, use a bidirectional LSTM framework to extract features and use the wide and deep model to do the multi-label classification for higher accuracy (88-93%).


pip install wide_and_deep

How to use

See demo

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

wide_and_deep-1.0.0.tar.gz (4.5 kB view hashes)

Uploaded source

Built Distribution

wide_and_deep-1.0.0-py3-none-any.whl (9.2 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page