Downloads · 30 days
0
SanaullahTareen07/symbolic-seem-neuro-ai-and-lstm-stock-price-prediction
symbolic-seem-neuro-ai-and-lstm-stock-price-prediction is a machine learning model from SanaullahTareen07. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Combines neural forecasting (LSTM) with Knowledge Graph constraints via Quadratic Programming. Ensures predictions respect real-world limits — even during crises.
Downloads · 30 days
0
Access
Public
Updated Jul 4, 2026
Repo size
2.1 MB
Likes
0
Public
Click a slice to open those files.
.pth820 KB · 34%
From the Hugging Face model README
Combines neural forecasting (LSTM) with Knowledge Graph constraints via Quadratic Programming. Ensures predictions respect real-world limits — even during crises.
| Condition | Neural Baseline | Symbolic Seam |
|---|---|---|
| Normal markets | RMSE 3.698 | RMSE 3.695 (identical) |
| Black Swan crisis | 95.33% violations | 6.00% violations ✅ |
| Violations prevented | — | 938 / 1,050 |
pip install yfinance cvxpy torch pandas scikit-learn -q
jupyter notebook Neuro_Symbolic_Forecasting_Kaggle.ipynb
Neural models fail when rules change (tariffs, limits, regulations). Symbolic Seam enforces hard constraints at inference time without retraining.
Neuro_Symbolic_Forecasting_Kaggle.ipynb — Single notebook, all stagesIEEE_Symbolic_Seam_Full.docx — Full research papermodels_backup_50stock.zip — Trained model + configSanaullah Tareen | PAF-IAST | @SanaullahTareen
Full details in IEEE paper or Kaggle notebook.