I Built a BFIU-Compliant AML Detection System in Python (Here's Why the Kaggle Approach Doesn't Work

I Built a BFIU-Compliant AML Detection System in Python (Here's Why the Kaggle Approach Doesn't Work)

Most AML tutorials end with a confusion matrix and a 99% accuracy score. Here's why that doesn't work — and what I built instead. I've been working in fintech compliance data for a while. The one thing I kept noticing: every "fraud detection project" on GitHub or Kaggle uses the same dataset — the UCI credit card fraud dataset from 2013. It has 284,000 rows, 30 features labeled V1-V28, and approximately zero explanatory value for anyone who wants to understand how financial crime actually works. So I built something different. The problem with the standard approach Real transaction monitoring engines don't work like Kaggle competitions. They don't take a CSV, train a model, and output a probability score. They work like this: A rule engine runs first — deterministic, auditable, regulatory-cited rules that generate alerts Those alerts get scored and triaged by risk tier An ML layer reduces false positives among the high-risk alerts ...
Post a Comment

My Portfolio | Data Science & Machine Learning Projects

 

Turning Data into Action: My Project Portfolio

Welcome to my project showcase. This is where theory meets practice. Each project listed here represents a step forward in my learning journey, demonstrating my ability to handle data, extract insights, and build predictive models.

Project 1: [Your Project's Name - e.g., Exploratory Analysis of Global Literacy Rates]

(A compelling image or chart from the project)

A comprehensive analysis of global literacy data to identify trends and correlations between literacy rates and socio-economic factors.

  • Objective: To understand the key drivers of literacy rates across different regions and income levels.
  • Tech Stack: Python, Pandas, Matplotlib, Seaborn, Jupyter Notebook.
  • Key Achievements:
    • Collected and cleaned a multi-source dataset.
    • Performed detailed exploratory data analysis (EDA) to uncover significant patterns.
    • Created a series of compelling visualizations to communicate findings.

[Button: View on GitHub] [Button: Read the Blog Post]

(Add more projects in the same format as you complete them. For now, you can leave this section with just one template.)

Comments

Post a Comment