underfitting

Too simple model

Underfitting occurs when a statistical or machine learning model is too simple to capture patterns in the data.

An underfitting model performs poorly even on the data it was trained on, failing to learn meaningful relationships: The linear model was underfitting—it couldn't capture the curve in the data.

The opposite problem is overfitting, where a model learns the training data too well and fails on new examples.

technical

bias

Unfair inclination or prejudice

overgeneralization · capacity · regularization · hyperparameter · cross-validation · holdout · residuals · convergence · benchmark · diagnostic

modeling

oversimplification

Stripping complexity unfairly

expressiveness · flexibility · constraints · assumptions · rigid · restrictive

simplicity

oversimplified

Made misleadingly basic

basic · elementary · shallow · superficial · underdeveloped · unrefined · unsophisticated · crude · generic · incomplete

algorithms

regression

Return to former state

bagging · clustering

symptoms

inaccuracy

Lack of precision

unrepresentative · inadequate · insufficient

Opposites
model complexity/fit

underfittingoverfitting

Excess adaptation to samples

overtraining · overlearning · overcomplexity

model adequacy

underfittinggeneralization

Deriving principles from examples

convergence

Family

outfit, fitting, fitness, fitted, unfit, outfits, misfit, refit, fitter

Familiarity
Top 1,000,000
Profile
Used worldwide · Timeless · Abstract · Rated G