Space Regulatory Glossary AI & Data Science

feature engineering

noun

1. The process of selecting, transforming, and creating input variables (features) from raw data to improve the performance of machine learning models. Good feature engineering often matters more than model selection for classical ML tasks.
2. For regulatory filing classification, engineered features might include filing prefix patterns, document length, frequency band mentions, applicant filing history, and time since last modification. These structured signals can outperform LLM-based approaches for well-defined classification tasks.

Related terms

classification A machine learning task that assigns predefined labels or categories to input data. Classification models learn… anomaly detection A set of techniques for identifying data points, patterns, or events that deviate significantly from expected behavior.… data pipeline An automated sequence of data processing steps that moves information from source systems through transformation,…

Browse all terms in the Space Regulatory Glossary →