madigan
Unverified ML strategy on Multi by Hanwant. BotFinder score 18 out of 100.
Application of reinforcement learning in trading financial markets.
Source: github
BotFinder analysis pending.
madigan
Madigan Code Associated with the paper Reinforcement Learning for Trading in Financial Markets: Theory and Applications Aims This repository contains a framework for conducting experiments exploring the use of reinforcement learning in trading financial markets. With a focus on statistical arbitrage, the eventual goal is to create autonomous systems for making trading decisions and executing them. The process will be much like scientific inquiry whereby hypotheses will be succesively tested in a directed manner. To this end, robust software is needed to allow for the process of implementing, validating and deploying ideas, along without the necessary hardware to allow for running experiments. Approach Current approach consists of formalizing the trading problem/context in the Markov decision process (MDP) framework. An agent makes decisions in interacting with an environment via a defined action space, seeking to maximize rewards given by the environment. agent -> trader environment -> 'market', broker, exchange, data, participants action space -> buy/sell/hold, desired portfolio rew
⚠ 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)