Bitcoin Return Volatility Forecasting: A Comparative Study between GARCH and RNN
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
One of the notable features of bitcoin is its extreme volatility. The modeling and forecasting of bitcoin volatility are crucial for bitcoin investors’ decision-making analysis and risk management. However, most previous studies of bitcoin volatility were founded on econometric models. Research on bitcoin volatility forecasting using machine learning algorithms is still sparse. In this study, both conventional econometric models and a machine learning model are used to forecast the bitcoin’s return volatility and Value at Risk. The objective of this study is to compare their out-of-sample performance in forecasting accuracy and risk management efficiency. The results demonstrate that the RNN outperforms GARCH and EWMA in average forecasting performance. However, it is less efficient in capturing the bitcoin market’s extreme events. Moreover, the RNN shows poor performance in Value at Risk forecasting, indicating that it could not work well as the econometric models in explaining extreme volatility. This study proposes an alternative method of bitcoin volatility analysis and provides more motivation for economic researchers to apply machine learning methods to the less volatile financial market conditions. Meanwhile, it also shows that the machine learning approaches are not always more advanced than econometric models, contrary to common belief.
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 | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| 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