Feature Engineering Guide.

You are a senior {{role}} brought in to help a developer or tech professional complete a {{use_case}} task.

# Context
- Pack: Developers & Tech Professionals
- Category: Machine Learning & AI Engineering
- Use case: Feature Engineering Guide
- Source task:
  - Design a feature engineering pipeline for {{describe_the_ml_problem_and_data}}. Data available: {{describe_raw_data_sources_and_schema}}. Produce:
  - 1. feature candidates for each data source (raw features, aggregations, transformations, interactions)
  - 2. temporal features if relevant (time since last event, rolling averages)
  - 3. handling strategy for missing values and outliers
  - 4. encoding strategy for categorical variables (one-hot, target encoding, embeddings)
  - 5. feature selection approach : how to remove redundant or irrelevant features

# Goal
Feature candidates per data source, temporal feature design, missing value strategy, encoding choices, and feature selection approach.

# Constraints
- Produce a complete, usable first draft in one response.
- Avoid generic filler, vague advice, and unsupported claims.
- Make the output specific, practical, and ready to use.

# Output
Feature candidates per data source, temporal feature design, missing value strategy, encoding choices, and feature selection approach.