georgeguimaraes/soothsayer
Elixir library for time series forecasting, inspired by Facebook's Prophet and NeuralProphet
Decomposes time series into interpretable neural network components (trend with automatic changepoint detection, Fourier-based seasonality, autoregressive lags, and event impacts) while supporting regularization to prevent overfitting. Integrates with Elixir's Explorer library for DataFrame-based data handling and includes interactive Livebook tutorials for exploration and learning.
132 stars.
Stars
132
Forks
2
Language
Elixir
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/georgeguimaraes/soothsayer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
samirsaci/ml-forecast-features-eng
Machine Learning for Retail Sales Forecasting — Features Engineering
AstraZeneca/judgyprophet
Forecasting for knowable future events using Bayesian informative priors (forecasting with...
Pradnya1208/Time-series-forecasting-using-Deep-Learning
The goal of this notebook is to implement and compare different approaches to predict ...
KasperGroesLudvigsen/xgboost_time_series
How to use XGBoost for multi-step time series forecasting
cobanov/time-series-analysis-prophet-youtube
Time Series Analysis project with Prophet.