awesome-deep-trading

Why we included this project

If you are trying to get machine learning to make trading decisions, this curated index is a strong starting point because it gathers the scattered academic and open-source work on the topic into one organized place. The author has sorted papers by technique — CNNs, LSTMs, GANs, reinforcement learning, and high-frequency approaches — and paired them with working repositories, datasets, and simulation tools, so you can move from reading a method to finding code that implements it. That structure matters for practitioners because deep trading research is fragmented across finance journals, arXiv, and GitHub, and this list saves you the weeks of hunting. It is also a useful learning map for newcomers who want to understand which neural architectures have actually been applied to markets before they commit to building their own strategy. Just treat it as a research and discovery resource rather than a ready-to-run system, since the value here is in the curated pointers rather than in any single piece of software.