AML Data with Python

AI-generated illustration Bangladesh, 3 AM. My phone buzzed. The alert read: PEP match – BDT 12.4 million inbound transfer to a new corporate account. My supervisor’s voice crackled on the speaker: ‘We’ve got 30 minutes before the regulator’s audit team walks in. Explain this.’ My heart hammered. I stared at the transaction log – a single wire from a shell company in Chittagong, linked to a name that showed up in the BFIU’s “high‑risk PEP” list last year. The red flag was real, but the system had thrown *dozens* of similar alerts that turned out to be harmless relatives of the same politician. The audit team would see a mountain of false positives and wonder why we couldn’t separate wheat from chaff. The Hidden Problem: Bangladeshi PEP Data Isn’t Ready for Plug‑and‑Play Most off‑the‑shelf screening engines assume three things: Names are clean, Latin‑script, and consistently formatted. Sanctions lists are static, updated monthly. Local AML teams have a single, unified risk‑score thresh...

AI-generated illustration Bangladesh, 09/23/2026. My phone buzzed at 02:17 AM. The AML dashboard at bKash lit up with a red fire‑alarm: 5,432 alerts in the last 30 minutes. The system was choking. Our false‑positive rate had spiked from 12% to a staggering 68% overnight. I stared at the numbers, heart pounding, wondering if the BFIU audit deadline next week would turn into a nightmare. The Hidden Problem: Synthetic Test Data Isn’t Synthetic Enough We had built a tiny test harness months ago – a handful of hard‑coded CSV rows that mimicked a few typical MFS transfers. It was enough to convince the team that the rule set was solid. But when the regulator demanded a stress‑test of the entire rule engine, the harness fell apart. It didn’t cover: Cross‑border remittance patterns that bounce between Rocket, Nagad, and local banks Layered structuring attempts just under the BDT 100,000 threshold Entity‑resolution edge cases where a single phone number appears on three different accounts In ...

AI-generated illustration Bangladesh, 02:17 am. My phone buzzed. An email from BFIU: ‘Immediate audit – 150 flagged transactions pending review’ . My team’s sanctions screen had just exploded with false positives – 1,200 alerts for a $5 million daily volume. The regulator was breathing down our necks, senior management was threatening budget cuts, and I could hear the coffee machine sputtering in the background. I was staring at a dashboard that looked like a fireworks show. That night, I realized we’d built the wrong kind of filter. The Hidden Problem Behind the Noise Most banks in Bangladesh start with a “plug‑and‑play” sanctions list from the UN and OFAC, then sprinkle a few country‑code checks. It sounds sensible until you factor in three local quirks: Bangladeshi Mobile Financial Services (MFS) push billions through BDT 100,000 thresholds, but the BFIU only requires detailed SARs for transactions above BDT 5 million . Names are often transliterated from Bangla to Latin script, pr...

AI-generated illustration The Moment the Dashboard Went Red It was 09:15 on a humid Tuesday. My phone buzzed, the AML console lit up with 1,245 alerts in under a minute. The spike wasn’t random – the total flagged amount topped BDT 12 million, most of it clustered around a single merchant ID that processed 3,800 micro‑payments in the last 24 hours. My team stared, coffee gone cold, and the compliance manager whispered, “We’re about to get a BFIU audit tomorrow.” The room fell silent. That was the hook that pulled me out of my chair and into a frantic sprint to understand why the model we’d just deployed was blowing up our false‑positive budget. The Hidden Problem Behind the Numbers Most AML models I’ve seen in Bangladesh start with a textbook approach: train a gradient‑boosted tree on historic SARs, add a few rule‑based thresholds (BDT 100,000 MFS limit, high‑risk country flag), and call it a day. The reality is messier. Our fintech’s user base is 65 % unbanked, transaction velocity sp...

AI-generated illustration Real‑World Hook It was a rainy Thursday in Gulshan. My inbox pinged: "Need a PWA for my boutique, budget BDT 30,000, deadline 2 weeks" . The client, a 28‑year‑old fashion retailer named Riya, showed me her Shopify store loading at 7 seconds on 3G. She’d lost roughly BDT 12,000 in sales last month because customers abandoned carts. I replied, "I can make it offline‑first, under 2 seconds, for BDT 30,000." I signed the contract on Upwork, sent the first invoice, and started building. The Hidden Problem Most freelancers think pricing is just a math exercise: hours × rate + buffer. I did the same. I estimated 80 hours, set my hourly rate at BDT 400, added a 10% contingency, and landed on BDT 35,200. I rounded down to BDT 30,000 to look tempting. What I missed was the hidden cost of post‑launch support and the reality of Bangladeshi data plans. Riya’s customers use 3G most of the day, paying BDT 30 per GB. A PWA that still pulls a 5 MB bundle e...

AI-generated illustration Bangladesh, 03:12 AM. The BFIU dashboard flashes a red line: a burst of 27 transactions, each just under the BDT 100,000 MFS threshold, moving between five Rocket agent accounts in 45 minutes. The total? BDT 3,027,842. My heart skips. The alarm that should have screamed never did. I was staring at a structuring ring that had slipped through the cracks of our rule‑based engine. The Hidden Problem: Why Classic Threshold Rules Fail in Dhaka We all start with the obvious: set a hard limit at BDT 100,000, flag anything above. Works for big jumps, but not for the slow, steady drip that smurfs money across multiple agents. In Bangladesh the BFIU Circular 15/2023 explicitly calls out “multiple low‑value transfers to a single beneficiary within a short window” as a red flag, yet most AML platforms still treat each transaction in isolation. My first attempt was a naïve count‑per‑hour rule. If an account sends more than three transactions over BDT 95,000 within an hour...

Photo by Ricardo Gomez Angel on Unsplash Real‑World Hook It was 9 am on a rainy Tuesday in Dhaka. My client, a tiny transport cooperative that runs 12 minibuses across Gulshan, sent a frantic WhatsApp voice note: “The fare‑lookup app you built just froze for half the riders. We lose at least 200 BDT per hour!” They’d just spent BDT 12,000 on a Google Play listing that never got any downloads because the app wouldn’t work on the 3G phones their commuters still use. I stared at the crash logs, the analytics, and my own coffee‑stained notebook. The numbers were clear: 75 % of sessions timed out after 8 seconds . The client’s revenue hit a dent of roughly BDT 9,000 a day. I had to turn this around before the next fare‑collection cycle. The Hidden Problem Most indie developers treat PWAs like glorified static sites. They sprinkle a service worker, slap an addToHomeScreen prompt, and call it a day. In Bangladesh, that shortcut is a recipe for disaster. Three realities bite hard: 3G is stil...

AI-generated illustration It was a rainy Tuesday in Gulshan. My client, a boutique that sold hand‑embroidered saris on Daraz, sent me a frantic screenshot: "App store fees ate BDT 3,900 this month!" Their native Android build, updated three weeks ago, was draining their budget faster than a 3G connection drains a data pack. They’d spent BDT 150,000 on a freelancer’s “native app” and were now paying a 30% commission on every in‑app purchase. I felt the same knot I get when a cold email bounces – a mix of irritation and curiosity. The Hidden Problem Most Bangladeshi small businesses think “native = better”. They hear about push notifications, app‑store visibility, and assume the only way to reach a customer on a phone is through a downloaded binary. The reality? The cost curve for native apps is a steep cliff, especially when you factor in: Initial development (BDT 120‑180k for a basic Flutter app) Store‑submission fees (Google Play = BDT 1,500, Apple = USD 99/year) Annual upd...

AI-generated illustration It was 02:17 AM on a rainy Dhaka night. My phone buzzed with a BFIU alert: 12,000 transactions flagged under the BDT 100,000 threshold for mobile money agents. The system had just dumped an extra 1.3 million BDT into the daily alert queue. My inbox filled with SAR drafts, senior managers pinged me, and the compliance dashboard turned bright red. I realized the threshold we’d set two years ago was bleeding us dry. The Hidden Problem: Why “One‑Size‑Fits‑All” Thresholds Don’t Work in Bangladesh Most MFS providers start with the regulator‑mandated BDT 100,000 daily volume trigger. Easy to implement. Easy to audit. But the reality on the ground is messier than the rulebook. Agent banking clusters in Mirpur and Gulshan push 30 % of daily volume. Rural kiosks see spikes only during harvest festivals. Seasonal cash‑in flows from remittances spike at Eid. When you treat all agents the same, you end up with two beasts: A flood of false positives that drown genuine SAR...

AI-generated illustration It was a rainy Thursday in Dhaka. My client, a boutique tea shop in Mirpur, sent a frantic screenshot: ‘Orders are stuck at 0 % sync, customers see a blank cart after the network drops.’ The PWA I built for them was supposed to work even on the 3G networks that still dominate many neighbourhoods. Instead, after the first 5 minutes of offline use, the whole checkout flow froze. I stared at the error console and saw QuotaExceededError: DOM Exception 22 flashing like a warning light on a rickshaw. The Hidden Problem Most Indie Developers Miss When you first hear the term offline‑first , the mind jumps to localStorage . It’s easy, it’s synchronous, you can drop a string in a few lines and call it a day. But that convenience is a trap. In Bangladesh, data caps are tight, connections flicker, and users expect their carts to survive a whole afternoon of spotty 3G. localStorage caps at roughly 5 MB per origin, stores only strings, and blocks the main thread while r...

AI-generated illustration High‑Stakes Hook It was 02:17 am on a humid Tuesday in Dhaka. My phone buzzed with an urgent Slack ping: “$1.1 million inbound from Kolkata just cleared – no SAR filed.” I stared at the dashboard. The transaction volume spiked 27 % over the previous hour, yet our rule‑engine flagged nothing. The BFIU had a 48‑hour reporting window. I felt my heart race. If this slipped, the regulator would slam us with a hefty fine and a public reprimand. I slammed the desk, opened the raw logs, and began digging. Within minutes I saw a pattern: a series of 12 KB‑size micro‑deposits, each just under the BDT 100,000 threshold, hopping between three agent‑banking accounts before landing in a corporate wallet. The fraud ring had built a perfect “structuring” maze that our static thresholds never saw. The Hidden Problem Most banks and MFS providers in Bangladesh still rely on static, rule‑based alerts . They set a hard cut‑off – BDT 100,000 inbound, BDT 50,000 outbound – and hope...