CapnClenchJaw@lemmy.world 2 days ago
This is an interesting and smart use case for locally run (and properly siloed) AI. Kind of a “identify any brush tends when it comes to spending habits, with particular focus on discretionary spending and areas where I can save money”.
Have you tinkered with any LLMs for this? If so, which ones do better than others? I could see SLMs being really good for this eventually.
chazwhiz@lemmy.world 1 day ago
I played a bit with the basic concept of identifying and categorizing merchants by importing a transaction csv into google sheets and writing a custom function that called the OpenAI API, basically just passing the raw merchant string along with “What category of business is this?”. It did well, the next step would have been to add a step that compared to a predefined list of possible categories. I didn’t compare any models or other platforms though. This was last year so I might play with it again.