Supervised learning models, statistical models or hybrid models? A prediction of clean energy stock based on fear and fundamental factors
Bibliographic record
Abstract
This paper explores several time series models for predicting the S&P Clean Energy Index. We begin by identifying factors previously found to influence the clean energy market and use eXtreme Gradient Boosting (XGBoost) to rank and filter feature importance of variables, followed by further validation and variable selection using SHAP values. Next, we simulate future feature data using methods like Random Forest and Long Short-Term Memory (LSTM). For the LSTM-based simulations, the data is generated through a classification-then-prediction approach using the K-Nearest Neighbors (KNN) algorithm. To predict the index’s volatility, we employ statistical models such as AutoRegressive Integrated Moving Average (ARIMA) and Vector Autoregression (VAR). Additionally, we use advanced methods like LSTM, Supervised Autoencoder (SAE), and hybrid models such as Prophet Features and LSTM_Autoregressive(LSTM_AR). Each model’s parameter-tuning process will be explained in detail. Finally, we compared the models’ performance and prediction results, discussing their strengths and suitability for different scenarios. We confirmed that the Prophet-based models performed well on Random Forest simulated data when predicting both the trend and actual values of the S&P clean energy index.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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 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".