> It has a very crude tf-idf based categorization. I do have plans to improve it.
You could use the same algorithm that was used for spam filtering in my Linux Journal article from back in 2003[1]. I have thought about making a plugin to do it with MoneyDance but haven't gotten around to it. But I think it would be quite easy for you to integrate into Paisa if you are looking to do that sort of thing. I have actually made some improvements to the algorithm since then; let me know if you're interested...
You could use the same algorithm that was used for spam filtering in my Linux Journal article from back in 2003[1]. I have thought about making a plugin to do it with MoneyDance but haven't gotten around to it. But I think it would be quite easy for you to integrate into Paisa if you are looking to do that sort of thing. I have actually made some improvements to the algorithm since then; let me know if you're interested...
[1] https://www.linuxjournal.com/article/6467