Understanding Macroeconomic Dynamics: Big-Data Forecasting and the Effects of Oil Price Shocks
Bibliographic record
Abstract
This dissertation comprises three chapters. The first chapter compares macroeconomic forecasts of various machine learning models. The subsequent two chapters evaluate the response of unemployment and monetary policy to various oil price shocks. The first chapter evaluates the performance of an extensive set of machine learning algorithms in forecasting macroeconomic variables relative to benchmark econometric models. We conduct a pseudo-out-of-sample forecast for fifteen real, nominal, and financial variables. Machine learning models outperform the benchmark in forecasting real variables, attributed to their ability to handle nonlinearities, but perform worse in forecasting nominal and financial variables. They beat the benchmark during high volatility episodes, like recessions and the COVID-19 pandemic. Dimension reduction models frequently appear in the top five most accurate models for real variables, especially at longer horizons. In the second chapter, we utilize local projections to investigate the impact of structural oil price shocks on unemployment rates and spells across the United States, emphasizing both national and state-level variations. Oil supply shocks lead to long-run increases in the national unemployment rate, incidence, and short-term unemployment. In contrast, economic activity shocks reduce all unemployment rates and spells, especially in oil-producing states. Consumption demand shocks have minimal impact on unemployment rates and durations, while inventory demand shocks show only temporary effects on durations. The third chapter uses local projections to investigate the macroeconomic and monetary policy responses to adverse oil supply shocks. The Federal Reserve raises interest rates twice: on impact and ten months after the shock to counter ongoing high inflation. A net oil exporter, Canada raises interest rates sharply in response to the shock to counter inflation. Switzerland initially maintains steady interest rates to prevent Swiss Franc appreciation, followed by gradual rate increases to manage inflation as the exchange rate stabilizes. Despite these efforts, inflation remains high in Switzerland.
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 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.004 | 0.006 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".