The idea was straightforward. Other complicated AI algorithms like neural networks are highly uninterpretable in the way they accomplish their goal like producing text or image generation. We just train these model until we reach a satisfactory training (and validation) set performance. So maybe, by generating a super portfolio of great stocks, a bunch of indicators, and a robust optimization algorithm, it would create an AI-trading algorithm that the world has never seen before!
|
One month later and I’m happy to report that fully automated AI algorithms are not taking over the financial markets… yet.
|
This article will dive deeper into these results, what went wrong, and some avenues of future improvement. To get an idea of the motivation of this experiment and how it was set up using the NexusTrade platform, check out this article.
|
Disclaimer: The content provided in this post is for informational purposes only and is not intended as financial advice or a recommendation to buy or sell any securities. I am not a financial advisor. The insights and analysis shared are meant to demonstrate the capabilities of NexusTrade in automating financial research. It's important to conduct your own due diligence and consult with a professional advisor before making any investment decisions.
|
|
