Deep Reinforcement Learning with Positional Context for Intraday Trading
By Sven Goluža, Tomislav Kovačević, Tessa Bauman, Zvonko Kostanjčar
Rating
1323
Battle Count: 71
Relevance
9/10
Highly relevant for developing intraday trading strategies using advanced machine learning techniques. The model shows promising results across various assets and time periods.
Implementation Complexity
7/10
Requires understanding of deep reinforcement learning and financial markets. Implementation details are provided, but expertise in both fields is necessary.
Reproducibility
4/5
The paper provides detailed information on the model architecture, hyperparameters, and evaluation process. Data source is mentioned but not publicly available.
About this paper
Methodology: Deep Reinforcement Learning with Positional Context. Problem types: Reinforcement Learning, Time Series Forecasting, Financial Decision-Making, Intraday Trading.
The interactive Everscope explorer (charts, battles, favorites) loads below.