Hybrid Stock Price Forecasting with Stacked LSTM and Multi-Source Feature Fusion
Bibliographic record
Abstract
This study proposes a hybrid deep learning (DL) framework that integrates sentimentderived features from financial news with technical stock indicators to enhance stock price forecasting accuracy.Sentiment metrics, specifically polarity and subjectivity scores, were extracted from the Economic Times 2024 dataset using VADER and TextBlob, and combined with technical parameters within a modified Stacked Long Short-Term Memory (SLSTM) model capable of capturing sequential market dependencies.The proposed framework was tested on four major NIFTY 50 companies representing the IT, banking, pharmaceutical, and metal sectors.Experimental evaluation showed notable gains in prediction accuracy, with Mean Absolute Error (MAE) values ranging from 1.67 to 20.31, Root Mean Squared Error (RMSE) from 2.08 to 26.49, and R² consistently exceeding 0.96.Comparative results showed that models incorporating polarity and subjectivity variables outperformed those utilizing only compound sentiment, highlighting the importance of detailed linguistic cues.Overall, the study found that using multi-source features considerably improves prediction stability and accuracy.The proposed architecture provides a scalable, domain-flexible solution for sentiment-driven financial forecasting, facilitating the development of intelligent stock market (SM) decision-support systems.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".