Tweedie distribution
The Tweedie distribution is a family of exponential-dispersion probability distributions that includes compound Poisson-gamma and related discrete or continuous cases.
Ensemble Methods for Machine Learning
A Tweedie distribution is a family of exponential-dispersion distributions that, for 1<p<2, represents compound Poisson-gamma behavior with a mass at zero and positive continuous values.
- How it is used
- Models targets with a spike at zero and a right-skewed positive tail through a compound-distribution likelihood.
- How deep it goes
- Defines the power-family mapping and applies 1<p<2 through tuned GLM regression, without deriving the likelihood.
- Examples
- Uses rainfall and casual bike-user counts, inspecting zero spikes, right tails, log-transformed targets, and regression metrics.
- What you can do after
- Apply it via scikit-learn’s TweedieRegressor by tuning power and L2 regularization with cross-validation.
Read how Ensemble Methods for Machine Learning explains Tweedie distribution →
Machine Learning System Design
A family of exponential-dispersion probability distributions that includes several continuous, discrete, and compound Poisson-gamma cases.
- How it is used
- Frames Tweedie loss as a second-line experiment for predictive models involving count data.
- How deep it goes
- Defines the family through its distributional members and zero-continuous behavior without deriving its mathematics.
- Examples
- Uses normal, gamma, inverse Gaussian, scaled Poisson, and compound Poisson–gamma distributions as family cases.
Read how Machine Learning System Design explains Tweedie distribution →
Related concepts
- TweedieRegressorused by · TweedieRegressor is a scikit-learn estimator that fits generalized linear regression models with a Tweedie distribution and configurable power parameter.
- LightGBMused by · LightGBM is an open-source gradient-boosting framework for efficiently training tree-based machine-learning models.
- Poisson-gamma distributionuses · A Poisson-gamma distribution is a hybrid distribution combining a Poisson component for a point mass at zero with a gamma component for positive continuous values.
- count dataaddresses · Count data consist of nonnegative integer-valued observations representing numbers of events, items, or occurrences.
- Poisson distributionhas part · The Poisson distribution is a discrete probability distribution that models the count of events occurring independently at a constant average rate within a fixed interval or exposure.
- gamma distributionhas part · The gamma distribution is a continuous probability distribution over positive values, characterized by shape and scale or rate parameters.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.