microsoft/CASPR
CASPR is a deep learning framework applying transformer architecture to learn and predict from tabular data at scale.
This framework helps data scientists and machine learning engineers create predictive models for business applications more efficiently. It takes sequential customer data, such as transaction history, and automatically generates high-quality features. The output is a general representation of customer behavior that can be used to improve predictions for tasks like identifying churn risk or estimating customer value.
No commits in the last 6 months.
Use this if you are a data scientist or ML engineer building predictive models from sequential customer activity data and want to reduce the effort of manual feature engineering across multiple applications.
Not ideal if your data is not sequential or tabular, or if you need highly customized, domain-specific feature engineering that goes beyond general customer behavior representation.
Stars
40
Forks
4
Language
Python
License
MIT
Category
Last pushed
Feb 09, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/microsoft/CASPR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
siapy/siapy-lib
🥷 A Python package for efficient processing of spectral images
yueliu1999/Awesome-Deep-Graph-Clustering
Awesome Deep Graph Clustering is a collection of SOTA, novel deep graph clustering methods...
Tony607/Keras_Deep_Clustering
How to do Unsupervised Clustering with Keras
bourdakos1/CapsNet-Visualization
🎆 A visualization of the CapsNet layers to better understand how it works
loretoparisi/CapsNet
CapsNet (Capsules Net) in Geoffrey E Hinton paper "Dynamic Routing Between Capsules" - State Of the Art