{"slug":"crisis-early-warning","name":"Crisis early-warning model","family":"Crisis risk","status":"active","estimate":"A country-year vulnerability score for a systemic banking-crisis onset one to three years after the last observed feature year.","page":"/crises/early-warning","implementation":{"enginePaths":["engine/finweave_engine/layers/ews.py"],"producerPath":"scripts/build/build_ews.py","outputs":["data/parquet/crisis_ews.parquet","data/parquet/ews_eval.parquet","data/parquet/ews_coefficients.parquet"]},"methodology":[{"path":"engine/finweave_engine/layers/ews.py","lines":[1,79],"note":"build_features(), build_panel(), walk_forward(), and fit_full() define the lagged onset target, exclusions, blocked evaluation, gap benchmark, and final fit."},{"path":"docs/crises_methodology.md","lines":[21,71],"note":"Defines episode onsets, the chronology discipline, and the merge and overlap rules inherited by the crisis layer."},{"path":"src/app/crises/early-warning/page.tsx","lines":[331,477],"note":"Publishes the target, feature lags, sample rules, blocked walk-forward design, source vintage, and current-score interpretation."},{"path":"docs/analyst_methodology.md","lines":[199,205],"note":"Requires the gap-benchmark loss and model limitations to accompany any early-warning interpretation."}],"data":{"vintage":"6,864 scored observations for 204 economies from 1985 through 2025; model ews-1.0, vintage jst-r6(2020);lv-2026-wp2694(2023);bis-gap(2025-Q4);gmd-2026_06(cut2024), measured 2026-08-30","tables":["data/parquet/crisis_ews.parquet","data/parquet/ews_eval.parquet","data/parquet/ews_coefficients.parquet"],"sources":[{"label":"Jordà-Schularick-Taylor Macrohistory Database, Release 6","url":"https://www.macrohistory.net/database/"},{"label":"IMF Systemic Banking Crises Database, Laeven-Valencia 2026 vintage","url":"https://www.imf.org/en/Publications/WP/Issues/2026/05/08/Systemic-Banking-Crises-Database-1970-2025-575634"},{"label":"Bank for International Settlements, total credit and credit-to-GDP gaps","url":"https://data.bis.org/topics/TOTAL_CREDIT"},{"label":"Global Macro Database, release 2026_06","url":"https://www.globalmacrodata.com/"}]},"method":["For country-year t, every feature is realized at t-1 or earlier and the label is one when a systemic banking-crisis episode begins in t, t+1, or t+2. JST chronology is used for its 18 advanced economies and the Laeven-Valencia chronology for all others; chronologies are never mixed within a country.","Features cover the credit gap, three-year real credit growth, current account, three-year real house-price growth, three-year public-debt-ratio change, real GDP growth, and inflation. Training-fold winsorization, imputation, standardization, and missing indicators prevent later data from entering earlier scores.","Era-blocked walk-forward evaluation trains only where each three-year label window ends before a test block. The pooled comparable gap subset reports logistic AUC 0.6479599141016464 against 0.6794201861130995 for the BIS credit-gap benchmark, so the simple benchmark wins.","Current scores describe vulnerability configurations under a historical model. They are not forecasts that a country will experience a current event."],"equations":[{"label":"Three-year onset target","expr":"y(i,t) = 1 if an onset occurs in {t, t+1, t+2}, using features from t-1 or earlier"},{"label":"Walk-forward purge","expr":"for block T, train on t <= T - 3 and test on t in [T, T + 5)"}],"validation":["The score output contains 6,864 observations for 204 economies from 1985 through 2025 and carries model version ews-1.0 with the stored source vintage.","On the pooled gap-available subset, the model's logistic AUC is 0.6479599141016464 and the BIS-gap benchmark AUC is 0.6794201861130995. The benchmark wins and that loss is published.","The producer verifies pooled row counts and base rates against the written output and hand-recomputes current gauge scores from the stored preprocessing statistics and coefficients."],"limitations":["The onset chronologies end in 2020 for JST economies and 2023 for Laeven-Valencia economies, so later events cannot be learned by this model.","A country-year needs at least three of seven features. Missing values are not fabricated, but missingness indicators can contribute to the score.","Current deciles and probabilities are model-based vulnerability summaries with material false alarms and misses, not statements about current events or certain future crises."],"references":[{"citation":"Schularick and Taylor (2012), Credit Booms Gone Bust, American Economic Review 102(2): 1029-1061.","url":"https://doi.org/10.1257/aer.102.2.1029"},{"citation":"Bussière and Fratzscher (2006), Towards a new early warning system of financial crises, Journal of International Money and Finance 25(6): 953-973."},{"citation":"Laeven and Valencia (2026), Systemic Banking Crises Database: 1970-2025, IMF Working Paper 26/94."}],"endpoints":[{"path":"/api/methods/[slug]","example":"/api/methods/crisis-early-warning","method":"GET","returns":"Registry metadata, implementation paths, measured vintage, methodology evidence, validation, and limitations. No model observations or parquet contents."}],"lastVerified":"2026-08-30"}