Forecasting of Stock Prices Using Machine Learning Models
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Stock price prediction with machine learning is an oft-studied area where numerous unsolved problems still abound owing to the high complexity and volatility that technical-factors and sentiment-analysis models are trying to capture. Nearly all areas of machine learning (ML) have been tested as solutions to generate a truly accurate predictive model. The accuracy of most models hovers around 50%, highlighting the need for further increases in precision, data handling, forecasting, and ultimately prediction.In this paper we present the result of our work on high-frequency (every fifteen minutes) stock-price prediction using technical data with a number of exogenous variables. These variables are carefully chosen to reflect the conventional wisdom in a traditional stock analysis on historical trend, general stock market condition, and interest rate movement. Several simple machine learning (ML) algorithms were developed to test the premise that with the appropriate variables, even a simple ML model could produce reasonable prediction of stock prices. Therefore, the originality of our approach is a rational selection of relevant and useful features and also on-the-fly model re-training taking advantage of the human time scale of inference (price prediction) and moderate size of the models. Moreover we do not mix any trading strategy with our stock-price prediction experiments, to ensure that conclusions are not context-dependent.Systems that integrate and test sentiment and technical analysis are considered the best candidates for an eventual generalized trading algorithm that can be applied to any stock, future, or traded commodity. However, much work remains to be done in applying natural language processing and the choice of text sources to find the most effective mixture of sentiment and technical analysis. Work on this area will be included in the next phase of our research project and here we have summarized some of the most relevant existing works in this direction.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.011 | 0.016 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it