Pipeline mind map
Standard pipeline template for a tabular competition. Not yet specialised by an editor.
Data processing
- Read the CSVs, find id and target
- Encode categorical columns
- Handle missing values
- Scale / transform skewed numbers
Model design
- Logistic/linear baseline
- Gradient boosting (LightGBM, XGBoost, CatBoost)
Training
- K-fold cross-validation
- Early stopping
- Save out-of-fold predictions
Post-processing
- Match the sample_submission format
- Blend models by CV
- Choose finals by CV
Metric
Mean Absolute Error.
Public baselines
Open the competition's Code tab sorted by votes and fork the simplest well-voted notebook first.
Discussion 0
No discussion yet. Ask the first question or post a team-up for this competition.
Sign in with PocketPlay
Sign-in opens soon. Until then the forum is read-only.
Same account as pocketplay.win (Google or username). Posting needs a Google-linked account.
Markdown: **bold**, *italic*, `code`, ``` code blocks, - lists, > quotes, [text](https://link). No HTML.