AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

A benchmark of categorical encoders for binary classification

Federico Matteucci, Vadim Arzamasov, Klemens Böhm

NeurIPS 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use One-Hot, Sum, Binary, or Weight of Evidence rather than other encodersBinary classification with all evaluated ML models · 50 binary classification datasetsaverage rankImproved
Use One-Hot rather than other encodersDecision trees · Binary classification datasetsaverage rankMixed
Use Sum, One-Hot, Binary, or Weight of Evidence rather than other encodersLogistic regression · Binary classification datasetsaverage rankImproved
Encode categorical attributes rather than dropping themBinary classification pipelines · 50 binary classification datasetsperformanceImproved
Increase the number of datasets used in the benchmarkEncoder consensus rankings · Disjoint dataset samplesSpearman ranking replicabilityImproved
Use logistic regression rather than decision trees as the benchmark modelEncoder benchmark · Disjoint dataset samplesranking replicabilityImproved
Change aggregation from mean quality to median qualityEncoder consensus ranking · Binary classification datasetsSpearman correlation between consensus rankings: 0.8Mixed
Change the ML model from decision trees to SVMEncoder ranking · Binary classification datasetsSpearman correlation between rankings: 0.3Mixed
Use full pipeline tuning instead of no tuningML model-encoder pipeline · Binary classificationpipeline qualityImproved
Use full pipeline tuning instead of model tuningML model-encoder pipeline · Binary classificationpipeline qualityImproved
Use Min-Hash rather than One-HotEncoder for binary classification · Medium-sized tabular datasetsperformanceNo clear effect
Use Binary rather than One-Hot or Mean-TargetLogistic regression · Bank marketingperformanceHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy