Posts

Showing posts from May 9, 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

How I Uncovered Hidden Structuring Patterns in bKash Transactions with Python

-
Last quarter, while reviewing a batch of 80,000 MFS transactions for a leading fintech in Bangladesh, I noticed something odd. About 2% of the transactions were exactly BDT 99,000, just below the BDT 100,000 MFS threshold. I was intrigued. The core problem most practitioners miss When I was new to AML analysis, I focused on detecting obvious suspicious transactions. But I was wrong about this until I realized that structuring patterns, like the one I mentioned, can be a significant red flag. In my experience, most AML analysts miss these patterns because they are not looking for them. I recall a case where a customer was structuring transactions to avoid the BDT 100,000 threshold, and it took us months to detect. Background / why this matters in BD fintech context In Bangladesh, the BFIU guidelines require fintechs to report suspicious transactions, including those that involve structuring. The STR/SAR process is critical in preventing money laundering and terrorist financing. As an AM...
Post a Comment
Read more