Most of the world’s arabica coffee grows in one part of Brazil. If frost hits Minas Gerais, there is less coffee that year, and the price goes up. Nobody argues with that. The question I wanted to answer is whether you can see it coming early enough to trade it. That is what Alladin does. It is the model I built after Taciturn, and it works on a completely different idea. ...
To what extent can artificial intelligence be used to build a technical analysis trading system that predicts short-term price movements in commodity markets? 1. Introduction My project is Taciturn, a system I built that trades gold and silver on its own, day and night. I had never coded before, so I used AI (large language models: ChatGPT, then Claude) to write the code while I designed, directed and tested it. AI later became part of the system itself, and led to my final model, Alladin. ...
The Idea Crops care about the weather. A dry month in Iowa, frost in Minas Gerais or a strong El Niño changes how much corn, coffee or cocoa gets harvested — and prices follow. Alladin turns that into a trading signal. How It Works For nine commodities — cocoa, coffee, corn, soy, wheat, sugar, natural gas, orange juice and cotton — Alladin pulls daily weather for the regions that actually grow or consume them, from Open-Meteo’s ERA5 reanalysis: ...
Where It Started Taciturn started whilst I was starting out trading, the idea came in the vision of a terminal that could give me financial insights on what the market of my choice was doing, whether it was near the daily high or daily low, and after coding a trend manager i could receive financial call outs via this terminal, telling me to buy or sell there was alot of other infomation which id look at usually whilst trading such as session deltas, yesterdays highs and lows, data id usually look at manually this was about 700 lines of code no broker integration no execution ...
Shelved, September 2026. This page is kept as a record of what I built and learnt. Where It Started Taciturn started whilst I was starting out trading, the idea came in the vision of a terminal that could give me financial insights on what the market of my choice was doing, whether it was near the daily high or daily low, and after coding a trend manager i could receive financial call outs via this terminal, telling me to buy or sell there was alot of other infomation which id look at usually whilst trading such as session deltas, yesterdays highs and lows, data id usually look at manually this was about 700 lines of code no broker integration no execution ...