📉  Continuous Probabilistic Forecasts

Continuous Probabilistic Forecasts#

Forecasts expressed as continuous probability distributions over outcomes.

Important

✨ AI-generated content. This page was written with the assistance of an AI language model and is provided as a learning aid. Despite careful review, it may still contain mistakes, omissions, or out-of-date information. Whether you are new to the topic, a team lead, or a senior practitioner, treat it as a starting point rather than an authoritative reference: read it critically and independently verify anything you act on (code, commands, figures, and factual claims) against official documentation and primary sources before relying on it.

What it is#

A continuous probabilistic forecast is a probabilistic forecast for a continuous (real-valued) outcome — a full predictive distribution over the variable (a density or CDF), rather than a single value or a class probability. It answers what is the whole distribution of tomorrow’s demand, price, or temperature?

How it’s represented#

It can be given as a parametric distribution (e.g. a normal \(\mathcal{N}(\mu, \sigma^2)\) with a forecast mean and variance), a set of quantiles, or an ensemble of sampled trajectories — each a way to describe the continuous outcome’s uncertainty.

Why it’s useful#

From one object it exposes every downstream quantity — the mean, any quantile, a prediction interval, or a tail probability. Because it lives on a continuum (unlike a discrete / categorical probabilistic forecast), it is scored with the CRPS.


Theme: Risk & Probabilistic Forecasting  ·  All terminology



See also

Source article Adapted (context, re-expressed) in our own words from: Continuous Probabilistic Forecasts (insightful-data-lab.com).

Tags: purpose: reference topic: terminology level: advanced