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>

man/generate_model_inputs.Rd

@@ -0,0 +1,27 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/functions.R
+\name{generate_model_inputs}
+\alias{generate_model_inputs}
+\title{Generate Resampled Model Inputs}
+\usage{
+generate_model_inputs(
+  feature_prefix = "04_feature/variant=Base",
+  out_prefix = "05_model_input",
+  bucket_name = "baf-fraud"
+)
+}
+\arguments{
+\item{feature_prefix}{Character. Input prefix (e.g., "04_feature/variant=Base").}
+
+\item{out_prefix}{Character. Output prefix base (e.g., "05_model_input").}
+
+\item{bucket_name}{Character. Bucket name. Default "baf-fraud".}
+}
+\value{
+Character. The output prefix (for targets dependency tracking).
+}
+\description{
+Reads the engineered feature layer, prepares a base tidymodels recipe,
+and generates resampled datasets (Baseline, Under, SMOTE, Adasyn, Tomek)
+across all months, saving them to the 05_model_input prefix.
+}