simon-hirsch/ondil
A package for online distributional learning.
This tool helps financial analysts, forecasters, and risk managers make predictions where the entire probability distribution of a variable (like stock prices or electricity demand) matters, not just the average. You input your observational data, and it outputs updated models that describe how factors influence the expected value, volatility, and even skewness or tail behavior of your target variable. This is for professionals who need to understand and predict the full range of possible outcomes, especially in streaming data environments.
Used by 1 other package. Available on PyPI.
Use this if you need to continuously update complex regression models that predict not just the average of an outcome, but also its full probability distribution (e.g., its spread, shape, and tail behavior) using streaming or very large datasets.
Not ideal if you only need to predict the mean of a variable with traditional regression and don't require understanding its full conditional probability distribution or updating models with new data incrementally.
Stars
32
Forks
7
Language
Python
License
GPL-3.0
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Dependencies
4
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/simon-hirsch/ondil"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
SimonBlanke/Gradient-Free-Optimizers
Lightweight optimization with local, global, population-based and sequential techniques across...
Gurobi/gurobi-machinelearning
Formulate trained predictors in Gurobi models
emdgroup/baybe
Bayesian Optimization and Design of Experiments
heal-research/pyoperon
Python bindings and scikit-learn interface for the Operon library for symbolic regression.
osqp/osqp
The Operator Splitting QP Solver