Intraday Stock Price Prediction using Machine Learning: A Case Study on YFinance Stock Data
Bibliographic record
Abstract
This paper explores short-term stock price forecasting using high-frequency 2-minute interval data for Apple Inc. (AAPL), focusing on the application and evaluation of three predictive modeling approaches: Linear Regression, XGBoost, and Long Short-Term Memory (LSTM) neural networks. The dataset, collected via Yahoo Finance (YFinance API), was enriched with technical indicators, rolling statistics, and lag features to support predictive learning. The models were evaluated on their ability to predict the next closing price and directional movement. While Linear Regression achieved the highest R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> score (0.9778) and lowest MSE (0.0502), XGBoost demonstrated competitive performance and provided valuable insights into feature importance. LSTM, though promising for capturing sequential dependencies, underperformed with a higher MSE (0.2490) and reduced R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> (0.8932), likely due to the noisy and highly volatile nature of intraday data. All models showed limited directional accuracy (~52%), highlighting the challenge of predicting micro-movements in high-frequency financial time series. This study concludes with a discussion on the strengths and limitations of each approach and outlines future improvements including feature selection, hybrid modeling, and enhanced data preprocessing to boost intraday forecast reliability.
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 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 | 0.029 | 0.046 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.007 |
| Science and technology studies | 0.002 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.004 | 0.005 |
| Research integrity | 0.000 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".