090°Données ouvertes
Jeux de données ouverts, entièrement documentés — interrogeables ici, et lisibles par n’importe quel LLM.
Les titres et les descriptions proviennent des sources de données, en anglais.
80 jeux de données
Business & Consumer Confidence Signals (derived)
Monthly economic-sentiment signals derived from the OECD's standardised business and consumer confidence indicators (amplitude adjusted, long-term average = 100; 56 countries and aggregates): 30-month annualized change volatility, 3-month momentum, 3-sigma anomaly flags vs a trailing 12-month baseline, naive-drift 1-month forecasts, a per-month cross-series volatility rank, the business-minus-consumer confidence gap (the demand-mismatch gauge), consecutive-months-below-100 pessimism streaks and 24-month sentiment z-scores. All rows carry canonical country_code so they join cleanly with other macro datasets. Derived keyless from the local raw oecd_cli catalog snapshots; underlying data: OECD (commercial re-use requires prior permission).
Consumer Pulse Signals (derived)
Signals derived from FRED's US consumer series: 30-period annualized volatility of monthly changes, 3-month momentum, year-over-year percent change, 3-sigma anomaly flags, naive-drift 1-month forecasts, a per-month cross-series volatility rank, and the University of Michigan sentiment z-score versus its trailing 12-month window. Covers UMCSENT (consumer sentiment index), TOTALSA (total vehicle sales, SAAR) and RSXFS (advance retail sales). All rows are normalized to country_code USA so they join cleanly with US macro data. Raw series: Federal Reserve Bank of St. Louis (FRED).
Producer Price Signals (derived)
Monthly ML-enriched producer-price signals for 35 economies, derived from OECD Key Economic Indicators: producer price year-over-year inflation, consumer price year-over-year inflation, and the PPI-minus-CPI spread (the margin-squeeze / cost-push gauge), with 30-month annualized change volatility, 3-month momentum, 3-sigma anomaly flags versus a trailing 12-month baseline, naive-drift 1-month forecasts, and a per-month cross-country volatility rank. Raw indicators: OECD. All rows carry ISO alpha-3 country_code and join cleanly with other macro datasets.
Bank Credit Cycle Signals (derived)
Signals derived from FRED's US bank-credit series: 30-period annualized volatility of changes, 3-month momentum, year-over-year level change, 3-sigma anomaly flags, naive-drift 1-month forecasts, a per-date cross-series volatility rank, and a delinquency stress-regime flag (1 when the real-estate delinquency rate exceeds its trailing-5-year 75th percentile) mapped onto every row's quarter. Covers TOTLL (weekly bank credit of all commercial banks), BUSLOANS (monthly commercial & industrial loans), REVOLSL (monthly consumer credit outstanding) and DRALACBN (quarterly delinquency rate on all real-estate loans). All rows are normalized to country_code USA so they join cleanly with US macro data. Raw series: Federal Reserve Bank of St. Louis (FRED).
Crypto Market Signals (derived)
Daily crypto market signals derived from CoinGecko's keyless free API for the 10 largest cryptocurrencies by market capitalization: 30-day annualized volatility, 3-month momentum, 3-sigma anomaly flags, naive-drift 1-month forecasts, a per-day cross-crypto volatility rank and the trailing-365-day drawdown gauge. Keyed to WLD (World); raw prices: CoinGecko (keyless free tier).
Sovereign Debt Signals (derived)
Annual ML-enriched sovereign debt signals for ~190 economies, derived from IMF World Economic Outlook data: government gross debt (% of GDP), 1-year and 5-year debt changes (percentage points), the current account balance (% of GDP) for twin-deficit analysis, 30-period change volatility, 3-year momentum, 3-sigma anomaly flags versus a trailing 10-year baseline, naive-drift 1-year forecasts, and a per-year cross-country volatility rank. Raw indicators: International Monetary Fund (World Economic Outlook); signals computed locally. All rows carry ISO alpha-3 country_code and join cleanly with other macro datasets.
Debt-Service Stress Signals (derived)
Quarterly financial-stress signals derived from BIS debt service ratios (keyless SDMX, WS_DSR, ~30 economies, 1999 ->): the DSR (interest + amortisation over income, %) for households, non-financial corporations and the private non-financial sector, with quarter-on-quarter and year-on-year changes, 30-quarter change volatility, 3-sigma anomaly flags vs a trailing-12-quarter baseline, drift forecasts, per-quarter cross-country volatility ranks, 10-year DSR z-scores, high-stress and rising-burden flags, and the household-minus-corporate sectoral spread. The debt-burden-stress companion to the credit-cycle gap signals. Country codes normalized to ISO alpha-3. Raw data: Bank for International Settlements.
Euro Effective Exchange Signals (derived)
Value-added euro valuation signals derived from the free European Central Bank effective-exchange-rate statistics: nominal and real (CPI-deflated) EER deviation from trailing-10-year means, valuation z-scores with overvalued-regime flags, 3-month momentum, 12-month volatility and 3-sigma anomaly flags — a compact euro-valuation dashboard for FX watchers. All computation is local pandas/numpy; no paid models or APIs.
EM Currency Stress Signals (derived)
Signals derived from FRED's daily emerging-market FX series (local currency per USD) for India, Brazil, South Korea and Thailand: 30-day annualized log-return volatility, 63-day depreciation momentum, 1-year depreciation, drawdown depth vs the trailing 1-year high, 3-sigma currency-shock anomaly flags, naive-drift 21-day forecasts and a per-day cross-currency volatility rank. The EM-stress companion to the broad US-dollar-strength signals. All rows carry canonical country_code so they join cleanly with country-keyed macro data. Raw series: Federal Reserve Bank of St. Louis (FRED), underlying data Federal Reserve Board.
ENSO Climate-Oscillation Signals (derived)
Monthly ENSO signals derived from the NOAA Climate Prediction Center (ONI, Nino 3.4 SST anomaly, and Southern Oscillation Index, 1950 ->): 3-month changes, 30-month change volatility, 3-sigma anomaly flags vs a trailing-10-year baseline, naive-drift 1-month forecasts, per-month cross-series volatility ranks, 10-year anomaly z-scores, and El Nino / La Nina phase flags (ONI +/-0.5C thresholds). The global ocean-atmosphere driver companion to the surface-climate signals. Raw data: NOAA Climate Prediction Center (keyless, public domain).
Economic Policy Uncertainty Signals (derived)
Value-added policy-uncertainty signals derived from FRED's mirror of the Baker/Bloom/Davis Economic Policy Uncertainty indices (policyuncertainty.com): daily US EPU (1985 -> present) and monthly global EPU (1997 -> present). Each row carries change volatility, ~3-month momentum, year-over-year change, a trailing-1y uncertainty z-score with an elevated-uncertainty flag, 3-sigma anomaly flags, naive-drift 1-month forecasts, a per-date cross-series volatility rank, and the US-vs-world uncertainty divergence gauge. All computation is local pandas/numpy; no paid models or APIs.
US Equity Market Signals (derived)
Daily equity-market signals derived from FRED's US index and volatility series: 30-day annualized log-return volatility, 3-month momentum, trailing-1-year peak-to-trough drawdowns (the bear-market gauge, index series only), 3-sigma return anomaly flags, naive-drift 21-trading-day forecasts, a per-day cross-series volatility rank, and the VIX 1-year z-score (the fear-regime gauge). Covers the S&P 500, the Dow Jones Industrial Average, the NASDAQ Composite and the CBOE Volatility Index. All rows are normalized to country_code USA so they join cleanly with US macro data. Raw series: Federal Reserve Bank of St. Louis (FRED).
Une fois l’allocation gratuite du jour épuisée, les fonctions d’IA peuvent passer par votre propre compte fournisseur.
Conservée uniquement dans cet onglet (effacée à sa fermeture) et envoyée avec chaque requête d’IA. Nos serveurs l’utilisent pour cette requête et ne la stockent ni ne la journalisent jamais.