FinanceLab Methodology
How the FinanceLab narrative attention indexes are built, validated, and cited.
What the index measures
Each index tracks daily media attention to a market theme - how much of the world's relevant news coverage is about it - indexed to 100 = its own historical average. A reading of 200 means roughly twice the usual attention; 80 means below-average. It is a descriptive measure of coverage, not a price or a forecast.
Data & construction
Source. Global news from GDELT, passed through a relevance gate that keeps only market-relevant articles (curated outlet list; the gate hits ~96-100% precision vs ~50% for keyword filters).
Labels. Each article is classified by domain, region, and impact severity, and scored for sentiment (FinBERT), by a distilled model.
Attention. The impact- and relevance-weighted share of the day's coverage in the theme, divided by the whole day's coverage (so it controls for overall news volume), then indexed to 100 = the full-history average.
Smoothing. A 7-day average for a clean daily series.
Spike detection & grounding
Spikes are genuine local peaks: detected by prominence over a local window (only bumps that rise clearly above their surroundings - a small move in a busy stretch is ignored), required to sit above the 100 baseline, and kept distinct (min 15 days apart). Every spike is grounded in the actual headlines that drove it, each linked to its source outlet.
Validation
Quality is measured, not asserted. Current results across the three indexes:
| Index | Below-baseline spikes | Known-event recall | Grounding relevance |
|---|---|---|---|
| Bank / Financial Stress | 0% | 100% | 76% |
| Energy & Oil-Risk | 0% | 75% | 92% |
| Crypto Attention | 0% | 100% | 100% |
Below-baseline: share of spikes below the 100 average (want 0%). Recall: major known events matched by a spike within a few days. Grounding: spikes whose headlines contain on-topic terms. (Energy recall reflects that oil attention peaked on the US oil-ban date, not the invasion day.)
How to cite
FinanceLab. [Index name]. https://financelab.ai/indexes/[slug] (data through [date]). A suggested citation appears on each index page.
Descriptive, not investment advice. These indexes measure news attention - descriptive analytics for research and context, not trading signals, forecasts, or investment advice.