Predict your time series with ETNA
ETNA is the first python open source framework of tbank.ru AI Center. It is designed to make working with time series simple, productive, and fun
pip install etna
Predict multiple time series from one domain
Optimized for large scale problems. With the all information about the process
Model zoo. At one place
Discover a variety of predictive models with unified interface: from classic machine learning to SOTA neural networks
Make feature generation easier
Generate time dependent features for both training and inference
Careful about the future
Temporal data structure always in mind. During preprocessing, training or inference
Built in tools for experiments
EDA, validation, hyperparameter optimization
Weights and Biases integration
Build better models faster with experiment tracking, dataset versioning, and model management
The future of business:
how we use ETNA at tbank.ru
Resource planning
We know in advance how many people we need
Financial Planning
Understand how company processes affect each other
Supply chain
There is always the right amount of money in ATMs
Problem solving
3 steps to make a profit for business
Predict using historical data
Cash in ATMs, number of support calls on each product
Analyze
Сash collection options, current resources
Make a decision
Date of encashment, recruitment and distribution of employees
Contacts
Report an issue with ETNA on GitHub
Join Telegram chat to discuss with real users