Three Essays in Macroeconomics with a Focus on Forecasting GDP Growth with Machine Learning, Measuring Uncertainty with NLP, and Revisiting a Small Open Economy RBC Model
Bibliographic record
Abstract
Chapter 1, entitled "Forecasting Canadian GDP Growth with Machine Learning," shows that it is possible to forecast Canadian monthly real GDP growth accurately ahead of the official release of GDP figures by Statistics Canada, by using, as predictors, Google trends (GT) data together with some Official data (such as employment) which are available before the official release of GDP data.This chapter uses some of the most recent supervised machine learning (ML) algorithms in order to forecast real GDP growth.The success of a supervised ML algorithm depends on its capability to capture nonlinearities in the relationship between the response variable and predictive variables as well as in the interactions between two predictive variables.Accordingly, in forecasting real GDP growth, we use nonlinear tree-based ensemble algorithms that have not been fully explored for economic forecasting, namely, eXtreme Gradient Boosting (XGBoost), CatBoost, Random Forest (RF) and Microsoft's Light Gradient Boosting Machine (LightGBM).We also use the nonlinear Support Vector Machine (SVM) algorithm, one of the best-known supervised ML algorithms for classification and regression analysis, which makes use of the nonlinear radial basis function as the kernel function.We use three data sets, namely, Official data, GT data and Official+GT data (a combination of the preceding two data sets).Feature selection is performed by either PDC-SIS, a variable selection procedure recently developed by Yousuf and Feng (2022) or XGBoost's "variable importance" measure (VI-XGBoost).The pre-selected features are then used together with the ML Bibliography
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 | 0.002 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.004 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.004 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.005 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".