Posts

Showing posts from May 13, 2026

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
Read more

Unmasking Money Laundering Networks in BD Fintech: My 8-Year Battle

-
Image
Photo by ThisisEngineering on Unsplash I still remember the night we discovered a massive structuring ring at one of the largest mobile financial services (MFS) providers in Bangladesh. It was a BDT 100 million case, with thousands of transactions flying under the radar. Our team had to act fast, but standard approaches weren't cutting it. We needed something more... sophisticated. The Hidden Problem As AML analysts, we're no strangers to false positives and noisy data. But in Bangladesh, the problem is exacerbated by the sheer volume of transactions. With bKash, Nagad, and Rocket leading the MFS charge, we're talking millions of transactions daily. The BFIU guidelines are clear: monitor transactions above BDT 100,000 , but that's just the tip of the iceberg. Why Standard Approaches Fail Traditional rule-based systems are too simplistic for our needs. They can't keep up with the complexity of modern money laundering networks. We need to think like the criminals...
Post a Comment
Read more