Why Can’t Neural Networks Forecast Pandemics Better
Bibliographic record
Abstract
Why can’t neural networks (NN) forecast better? In the major super-forecasting competitions, NN have typically under-performed when compared to traditional statistical methods. When they have performed well, the underlying methods have been ensembles of NN and statistical methods. Forecasting stock markets, medical, infrastructure dynamics, social activity or pandemics each have their own challenges. In this study, we evaluate the strengths of a collection of methods for forecasting pandemics such as Covid-19 using NN, statistical methods as well as parameterized mechanistic models. Forecasts of epidemics can inform public health response and decision making, so accurate forecasting is crucial for general public notification, timing and spatial targeting of intervention. We show that NN typically under-perform in forecasting Covid-19 active cases which can be attributed to the lack of training data which is common for forecasts. Our test data consists of the top ten countries for active Covid-19 cases early in the pandemic and is represented as a Time Series (TS). We found that Statistical methods outperform NN for most cases. Albeit, NN are still good pattern finders and we suggest that there are perhaps more productive ways other than purely data driven models of using NN to help produce better 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.
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 | 0.007 | 0.033 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.003 | 0.005 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 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".