Stock Price Prediction Using a Multivariate Multistep LSTM: A Sentiment and Public Engagement Analysis Model
Bibliographic record
Abstract
The impact of many factors on stock price has made the prediction of the stock market a problematic and highly complicated task to achieve. IoT analytics has enabled predictive analysis concerning the stock market, with internet search trends, reactions to current events, Twitter data, and historical stock returns as input data. Although inconsistencies remain as to which data sources are deemed most adequate, data preprocessing techniques have successfully overcome data integrity issues and unstructured data formats in specific applications. Additionally, advancements in computational power and machine learning technologies have led to the ability to handle tremendous amounts of information, accompanied by the growth of interest in this specific domain. In this paper, a Multivariate Multistep Output Long-Short-Term-Memory (MMLSTM) model is proposed to provide a one-week prediction on the stock close value for the technology company, “Apple Inc.” with the stock name “AAPL”. A large variety of data sources enabled by IoT platforms have been employed to model the impact of public sentiment and engagement on the closing price of this particular stock by looking at Google Search Trends, e-News headlines, and Tweets involving AAPL and its products. The proposed MMLSTM has improved the Mean Square Error (MSE) of up to 65% compared to ARIMA and Random Forest models. In addition, the proposed MMLSTM has outperformed most of the LSTM models introduced in the literature.
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) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| 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) | 0.002 | 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".