Application of Machine Learning With News Sentiment in Stock Trading Strategies
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
This study empirically tested the feasibility of machine learning in trading strategies using technical indicators and news information as the feature variables for machine learning. Six indicators were adopted in this study, including moving average (MA), moving average convergence/divergence (MACD), relative strength index (RSI), stochastic oscillator (KD), and on-balance volume (OBV), and news sentiment ratio (SR) developed in this study via text mining. Selected machine learning models, including support vector machine (SVM), eXtreme Gradient Boosting (XGBoost), recurrent neural network (RNN), and long short-term memory (LSTM), were also employed for investigation. This study backtested the daily historical data of the constituent stocks in the Taiwan Top 50 ETF from January 1, 2003, to December 31, 2018, using three categories of trading strategies along with conventional and countertrend operations. The following conclusions were drawn after analyzing the performance of these trading strategies via various means: 1. Technical indicators such as MA, MACD, and RSI performed poorly in most cases. 2. Specific parameters were of relative importance to several technical indicators, including MA, MACD, RSI, and OBV. 3. OBV was a technical indicator with a positive impact on trading strategies. 4. The machine learning-based XGBoost models were able to outperform trading strategies with technical indicators under specific scenarios. 5. SR, the news sentiment ratio developed in this study, could not significantly improve the performance of machine learning models. The empirical results of this study suggest that these machine-learning models are capable of analyzing long-term stock price movements to some extent.
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 | 0.016 | 0.012 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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