Initial commit: BAF Lakehouse fraud detection pipeline
End-to-end LightGBM fraud detection pipeline built as an R package, orchestrated by targets with data stored in MinIO via Apache Arrow. Includes 6-layer Lakehouse architecture, class imbalance tournament, formally tuned hyperparameters (PR-AUC 0.198), and Quarto RevealJS slides. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
BIN
reports/figures/fig_final_conf_mat.png
Normal file
|
After Width: | Height: | Size: 56 KiB |
BIN
reports/figures/fig_final_curves.png
Normal file
|
After Width: | Height: | Size: 151 KiB |
BIN
reports/figures/fig_fraud_by_month.png
Normal file
|
After Width: | Height: | Size: 106 KiB |
BIN
reports/figures/fig_hexbin_interaction.png
Normal file
|
After Width: | Height: | Size: 375 KiB |
BIN
reports/figures/fig_missingness.png
Normal file
|
After Width: | Height: | Size: 76 KiB |
BIN
reports/figures/fig_num_cor.png
Normal file
|
After Width: | Height: | Size: 291 KiB |
BIN
reports/figures/fig_strategy_showdown.png
Normal file
|
After Width: | Height: | Size: 95 KiB |
BIN
reports/figures/fig_var_imp.png
Normal file
|
After Width: | Height: | Size: 128 KiB |