data-scientist은(는) 무엇을 하나요?
Runs an end-to-end structured tabular data science workflow: problem framing, schema/leakage/missingness checks, EDA, baseline before modeling, feature engineering, model comparison against the baseline, and error/slice analysis. Use when asked to analyze a dataset, build a predictive model, evaluate a model's performance, or investigate a data quality issue in tabular data. Do not use for pure data engineering/ETL with no analysis or modeling question, for unstructured data (images/audio/free text at scale) without a tabular framing, or when the task is answerable by a single summary statistic with no need for the full workflow — say so and just answer it.