The benefits of forecasting inflation with machine learning: New evidence
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
Summary Medeiros et al. (2021) (Journal of Business & Economic Statistics, 39:1, 98–119) find that random forest (RF) outperforms US inflation forecasting benchmarks. We replicate the main results in Medeiros et al. (2021) and (1) considerably expand the set of machine learning methods, (2) analyse the predictive ability of both the initial and extended sets of methods on Canadian and UK data, (3) add results on coverage rates and widths of prediction intervals and (4) extend the sample from January 2016 to October 2022. Our narrow replication confirms the main findings of the original paper. However, the wider replication results suggest that other methods are competitive with RF and often more accurate. In addition, RF produces disappointing results during the coronavirus pandemic and subsequent high inflation of 2020–2022, whereas a stochastic volatility model and some gradient boosting methods produce more accurate forecasts.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| 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