Professional Forecasters vs. Shallow Neural Network Ensembles: Assessing Inflation Prediction Accuracy
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
Accurate inflation forecasting is crucial for effective monetary policy, particularly during turning points that demand policy realignment. This study examines the efficacy of dedicating ensembles of shallow recurrent neural network models to different forecasting horizons for predicting U.S. inflation turning points more precisely than traditional methods, including the Survey of Professional Forecasters (SPF). We employ monthly data from January 1970 to May 2024, training these ensemble models on information through December 2022 and testing on out-of-sample observations from January 2023 to May 2024. The models generate forecasts at horizons of up to 16 months (one ensemble per horizon), accounting for both short- and medium-term dynamics. The results indicate that such ensembles of recurrent neural networks consistently outperform conventional approaches using key performance metrics, notably detecting inflation turning points earlier and projecting a return to target levels by May 2024—several months ahead of the Survey of Professional Forecasters’ average forecast. These findings underscore the value of such ensembles in capturing complex nonlinear relationships within macroeconomic data, offering a more robust alternative to standard econometric methods. By delivering timely and accurate forecasts, dedicated ensembles of shallow recurrent neural networks hold great promise for informing proactive policy measures and guiding decisions under uncertain economic conditions.
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 | 0.007 | 0.005 |
| 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