EDiffusion-QL-Multimodal-Stock-Trading
Unverified ML strategy on Indices by simbovk. BotFinder score 18 out of 100.
This repository provides implementation of EDiffusion-QL: a diffusion-based reinforcement learning framework for multimodal stock trading.
Source: github
BotFinder analysis pending.
EDiffusion-QL-Multimodal-Stock-Trading
Enhanced Diffusion Policy for Robust Multimodal Stock Trading This repository contains the implementation of my B.Sc. thesis project, presented as: Enhanced Diffusion Policy for Robust Multimodal Stock Trading through the Integration of Technical Indicators and Fundamental News Amirali Vakili, Mahan Veisi, Mahdi Shahbazi Khojasteh, Armin Salimi-Badr IEEE conference paper, IICAI 2026 The project applies an Enhanced Diffusion-QL (EDiffusion-QL) framework to automated stock trading. The model combines technical indicators, financial news embeddings, a Bi-LSTM temporal state encoder, a diffusion-based actor, and twin Q-learning critics to generate robust continuous trading actions under volatile market conditions. --- Overview Financial markets are noisy, non-stationary, and influenced by both historical price behavior and external information. Standard deep reinforcement learning methods often rely on restrictive policy distributions, which may not capture the multi-modal nature of trading decisions. This project addresses that limitation by using a diffusion-based policy for action gen
⚠ No verified equity curve — no track-record source connected.
Drawdown profile
Data unavailable — contact the owner.
Verification ledger
How the score has moved
Recalculated at each data collection. Transparency means showing the bad weeks too.
No score history is stored yet — only the current score is shown.
Reviews & comments
No reviews collected from the source yet.
⚠ No live verification account connected — ask for proof before buying.
Alerts on changes: coming soon
Prop-firm compatibility not provided.
Open-source maintainer on GitHub.
Data-completeness & trust index (not a profitability rating)