Econometric models beat machine learning in volatility forecasts
A Federal Reserve Board study shows targeted econometric models outperform machine learning when forecasting realized volatility.
Adverse oil supply news shocks cause larger and more persistent contractions in real activity than favorable shocks produce expansions, according to research from Banco de España.
A Banque de France survey of 7,000 businesses shows 67 percent of French firms with at least 20 employees used generative AI at the start of 2026.
Regulators in six jurisdictions tailor prudential rules to the balance sheets of small lenders.
A South African Reserve Bank study shows that a one percentage point increase in the government debt-to-GDP ratio raises sovereign bond yields and the term premium by 12 basis points.
A Federal Reserve Board study shows targeted econometric models outperform machine learning when forecasting realized volatility.
Banque de France increased its green bond holdings to €21.6 billion at the end of 2025, up from €10.2 billion in 2024.
Official economic statistics can be cryptographically verified in one to two seconds using blockchain anchoring, according to a Bank for International Settlements study.
A carbon tax cutting emissions by 10 percent causes 56 percent higher welfare losses in rural areas than in Paris, according to a Banque de France study.
European banks with assets exceeding 50 percent of domestic GDP pay 30 percent lower credit default swap spreads, while global systemic designation provides no funding advantage, according to a De Nederlandsche Bank study of 32 institutions from 2008 to 2024.
Russian banks generated 2.3 trillion rubles in net profit during the first half of 2026, up 36 percent year-on-year, according to the Bank of Russia.
Shifts in the asymmetry of inflation risks generate persistent stagflationary dynamics by raising prices and depressing real economic activity, according to research from the Banco de España.