AI categorisation

Hey there

I hose Bubble to build a simple transaction categorisation app. Pulls in transactions from my bank account and allows me to categorise them into different spending categories (food, car, mortgage, etc).

The thing is, I have over 5 thousand categorised transactions now so there is a lot data there that could be used to train an AI model that could then be used to categorise future transactions.

I’m a relatively experienced Bubble dev but completely new to AI. Anyone got ideas on how I could train a model on my historical categorised transactions and then use it to categorise future transactions?

Hey Aaron,

I would suggest to make a first attempt with “few-shot” approach with an LLM, which is basically providing examples in the prompt so that the model has some reference (ej. Category X → Example 1, Example 2,… Category Y → …)

If it’s not accurate enough, you can go with fine-tunning a model. An easy approach is with de OpenAI developer portal, you can just upload a CSV with examples. This option is more expensive.