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>

deploy.R

@@ -0,0 +1,22 @@
+# deploy.R
+
+message("📝 1. Updating package documentation and namespace...")
+devtools::document()
+
+message("🚀 2. Running targets pipeline...")
+targets::tar_make()
+
+message("🏗️ 3. Building pkgdown website...")
+pkgdown::build_site()
+
+message("📦 4. Injecting slides into public docs/ folder...")
+# Create target directories
+fs::dir_create("docs/slides/reports/figures")
+
+# Copy the HTML and index_files
+fs::dir_copy("reports/slides/", "docs/slides/", overwrite = TRUE)
+
+# Copy the figures so the slides can see them
+fs::dir_copy("reports/figures/", "docs/slides/reports/figures/", overwrite = TRUE)
+
+message("✅ DONE: Site and slides successfully deployed to docs/")