intelligent-trading-bot VS cempaka

I agree that the conventional (numeric) forecasting can hardly benefit from the newest approaches like transformers and LLMs. I made such a conclusion while working on the intelligent trading bot [0] by experimenting with many ML algorithms. Yet, there exist some cases where transformers might provide significant advantages. They could be useful where the (numeric) forecasting is augmented with discrete event analysis and where sequences of events are important. Another use case is where certain patterns are important like those detected in technical analysis. Yet, for these cases much more data is needed.

[0] https://github.com/asavinov/intelligent-trading-bot Intelligent Trading Bot: Automatically generating signals and trading based on machine learning and feature engineering

While I was laid off and looking for work, I connected with a cryptocurrency market making firm that had access to a private broker feed which is not attached to any matching, so would occasionally go crossed and offer a pure arb opportunity for the same pairs. I had done some algo trading with Java in Kospi 200 options in 2011-2012 so I decided to put together a simple bot for them to try and grab the crossed markets when they occur. Even an incredibly simple trade like this requires quite a lot of work to get the risk management in place. I also took it as a chance to catch up on new Java features since I had been out of that ecosystem for awhile.

It did successfully grab the arbs but there wasn't enough juice to justify more work on it and I got a job in the meantime, so I open sourced the whole thing: https://github.com/abissell/cempaka