policy
Stock-Market-Research-Projects
RChahana · PyTorch
or hover any field below to flag it
Overview
Name
Stock-Market-Research-Projects
Author
RChahana
Framework
PyTorch
License
unknown
Skill type
other
Evidence level
untested
Task description
Built a sentiment-driven portfolio management system for 50 US & 50 Indian companies. Used GDELT & NewsAPI with FinBERT for sentiment scoring, and Yfinance for 2-year stock data. Trained LSTM, LSTM-CNN & RL (SAC, PPO). Evaluated with Sharpe, Sortino, Calmar ratios; hybrid model achieved best risk-ad
Spaces
Action space
other · 0-dim · 0Hz
Observation space
- type: other
Links
HuggingFace repo
null
Paper (arXiv)
null
Compatible robots
3+17 mentioned but not in catalog yetCompatible environments
0No environments list Stock-Market-Research-Projects yet.
Datasets that reference this policy
0No datasets reference Stock-Market-Research-Projects yet.