ml-stock-prediction
Unverified ML strategy on Indices by GuilhermeGSousa. BotFinder score 18 out of 100.
A toolset for stock prediction using reinforced learning, including a custom OpenAI environment.
Source: github
BotFinder analysis pending.
ml-stock-prediction
ml-stock-prediction This repository aims to use Reinforcement Learning to backtest and live trade cryptocurrencies with custom OpenAI Gym environments. Prerequisites ============= To get this project up and running on your machine, and mainly to be able to use the trading environments, a few dependencies must first be installed. Firstly to install if not already installed NumPy, Pandas, Jupyter and matplotlib by doing: OpenAI Gym must also be installed, which can be done with: Please refer to the OpenAI Gym repo for more information. To get historical data, place orders or making other requests from GDAX, the unoficial GDAX python client by Daniel Paquin is used, which can be installed once again using pip: OpenAI Environments =================== The testing environment Similarly to other OpenAI environments, this one can be instanced by It uses GDAX historical data from January 2017 to March 2018, and a start date can be specified when reseting the environment. A random start date is otherwise chosen. One episode represents one month starting at date with timesteps of 15 minutes. Ev
⚠ 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)