Sibyl
Unverified ML strategy on Indices by junosan. BotFinder score 18 out of 100.
Platform for backtesting and live-trading intraday Stock/ETF/ELW using recurrent neural networks
Source: github
BotFinder analysis pending.
Sibyl
Sibyl Sibyl (Simulation of Intraday Book and Yield with Limit-orders) is a platform for backtesting and live-trading with real-time intraday Stock/ETF/ELW data, with a special focus on training and evaluating recurrent neural networks (RNNs) for forming trade signals. It adopts a server/client model with a TCP communication channel, allowing exactly the same code to be used for both backtesting and live-trading, on distributed systems or within the same system. - Server side - backtesting simulator - agent for relaying order request/status to/from a broker - Client side - order request generators using RNNs (for real-time) - order request generators using pre-calculated reference target signals (for testing) Requirements Project was developed using g++ 5.4.0 with -std=c++11. Version numbers are not hard requirements. RNN backends - Fractal (commit 261f1fd) : based on C++/CUDA; faster than Sophia - Sophia (commit 3ab4359) : based on Python/Theano; less VRAM usage than Fractal, and more flexibility in experimental RNN structures - Theano (0.9.0b1) with libgpuarray (0.6.0) : symbolic co
⚠ 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)