Rules, Models, and the Tradeoffs Between Them
The more I learn about fraud, the more I realize how much of banking is shaped by the people trying to exploit it. Fraud isn't a side problem. It influences how accounts are opened, how transactions are monitored, how clients are verified, and how much friction everyone tolerates along the way.
Finding Natural Groups in Transaction Data
All the attention right now is on large language models. But there's a whole category of machine learning that's been quietly useful for years and doesn't require a GPU or a billion parameters. Clustering is one of those techniques. The idea is simple. Given a pile of client data, can an algorithm find natural groups without being told what to look for? I wanted to try it.
Digging Into the Mechanics
After two weeks of playing with ChatGPT, I hit a point where "wow, it's good" wasn't enough. I wanted to understand what's actually happening when I type a prompt and get a coherent response. Not at a PhD level, but enough to move past treating it like a black box.
Something Just Changed
I wasn't prepared for ChatGPT. OpenAI released it on November 30th, it hit a million users in five days, and I signed up expecting the usual chatbot experience. Ask it something, get a mediocre response, close the tab. That is not what happened.
