Evaluating Predictive Models for Three Green Finance Markets: Insights from Statistical vs. Machine Learning Approaches
Bibliographic record
Abstract
As climate change has become of eminent importance in the last two decades, so has interest in industry-wide carbon emissions and policies promoting a low-carbon economy. Investors and policymakers could improve their decision-making by producing accurate forecasts of relevant green finance market indices: carbon efficiency, clean energy, and sustainability. The purpose of this paper is to compare the performance of single-step univariate forecasts produced by a set of selected statistical and regression-tree-based predictive models, using large datasets of over 2500 daily records of green market indices gathered in a ten-year timespan. The statistical models include simple exponential smoothing, Holt’s method, the ETS version of the exponential model, linear regression, weighted moving average, and autoregressive moving average (ARMA). In addition, the decision tree-based machine learning (ML) methods include the standard regression trees and two ensemble methods, namely the random forests and extreme gradient boosting (XGBoost). The forecasting results show that (i) exponential smoothing models achieve the best performance, and (ii) ensemble methods, namely XGBoost and random forests, perform better than the standard regression trees. The findings of this study will be valuable to both policymakers and investors. Policymakers can leverage these predictive models to design balanced policy interventions that support environmentally sustainable businesses while fostering continued economic growth. In parallel, investors and traders will benefit from an ease of adaptability to rapid market changes thanks to the computationally cost-effective model attributes found in this study to generate profits.
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 | 0.009 | 0.016 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 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 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".