Price_Prediction_LOB
Unverified ML strategy on Multi by Jackmzw. BotFinder score 18 out of 100.
Deep learning for price movement prediction using high frequency limit order data
Source: github
BotFinder analysis pending.
Price_Prediction_LOB
Price Trend Prediction Using Deep Learning This software implements the Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) to predict the price movement using high frequency limit order data. For details, please refer to my report Price Trend Prediction Using Deep Learning. Requirements - The program is written in Python, and uses pytorch, scikit-learn, pandas and numpy. - If necessary, run pip install -r requirements.txt. - A GPU is not necessary, but can provide a significant speed up especially for training a new model. Usage RNN model This example trains a multi-layer RNN (Basic or LSTM) on a price movement prediction task. The code is tested under Windows 10 Anaconda 3 and reproducible. After training, it will print out the performance measures in test set, as well as the plots of loss and kappa in both train and valid set after each epoch. During training, if a keyboard interrupt (Ctrl-C) is received, training is stopped and the current model is evaluated against the test dataset. The rnn.py script accepts the following arguments: CNN model Training CNN model
⚠ 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)