notadamking/RLTrader

Allow user-defined prediction models to replace SARIMAX with LSTM, FB Prophet, etc.

Open

#15 opened on Jun 7, 2019

View on GitHub
 (2 comments) (0 reactions) (0 assignees)Python (535 forks)batch import
enhancementgood first issuehelp wantedquestion

Repository metrics

Stars
 (1,592 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

Instead of using the SARIMAX model's predictions to be fed as a feature / observation into the agent at every time step, maybe using the predictions of a separately trained LSTM may perform better. I've found that LSTM's trained on stationary time series usually perform ok, in that their prediction "direction" (up or down) is generally correct. Also, the slope (change in log returns with respect to time) of the LSTM prediction can be used as an additional input feature as an indicator for the severity of the predicted change (will the price jump up or down suddenly?).

Contributor guide

Research direction
Examine the existing SARIMAX integration in the RLTrader codebase to understand how predictions are fed to the agent. Review the two comments on this issue for additional context. Then design a generic interface for user defined prediction models, such as LSTM or FB Prophet, that can replace SARIMAX. Consider using libraries like PyTorch or TensorFlow for LSTM and ensure compatibility with the existing trading environment.
Tech stack
python
Domain
machine learning
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
4
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Over 1 week
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Needs investigation
Prerequisites
Python programmingReinforcement learning basicsTime series forecastingDeep learning (LSTM)
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
25