feature-engineering-automation-incomplete-revolution
IN derived (depth 1)
Created 2026-06-21T11:27:22+00:00 · Reviewed 2026-06-21T15:37:01+00:00
ML's automation of feature engineering is an incomplete revolution — deep learning reduces but does not eliminate manual feature engineering, automated methods (DFS) can outperform most human teams but not all, and production systems still require centralized feature stores for managing features across training and inference, suggesting that full representation learning has not eliminated the need for human-engineered features in structured and tabular domains.
Justifications
SL — Three independent indicators (incomplete automation, imperfect automated performance, continued infrastructure investment) all point to feature engineering surviving deep learning's representation learning claims
Antecedents (all must be IN):
- IN deep-learning-reduces-but-does-not-eliminate-feature-engineering — Deep learning reduces but does not eliminate the need for feature engineering — representation learning automates some feature construction but manual engineering remains valuable for structured and tabular data.
- IN deep-feature-synthesis-beat-615-of-906-human-teams — Deep Feature Synthesis (DFS) beat 615 of 906 human teams in an automated feature engineering competition.
- IN feature-store-centralized-repo-training-and-inference — A feature store is a centralized repository for storing, organizing, versioning, and serving features for both model training and production inference.
Dependents
These beliefs depend on this one:
- IN feature-engineering-persistence-reflects-theory-incompleteness — The persistence of manual feature engineering despite deep learning's partial automation suggests that ML's surviving theoretical anchor — the manifold hypothesis — may share a similar incompleteness: just as representation learning reduces but does not eliminate the need for human-engineered features (particularly in structured and tabular domains), the manifold hypothesis provides foundational architectural guidance but may not fully characterize the structure of all data encountered in practice.