FAQ

A cross-domain forecasting site: we track real public data across economics, health, education, and more, look for genuine lead-lag relationships between indicators, and turn those into plain-language, falsifiable forecasts — dated and published before we know if they're right.

We run correlation and lag analysis (Pearson correlation, screened across time lags) on real historical data to find indicators that tend to move before others, then use that relationship plus the latest real readings to project forward. We don't run anything more exotic than that — no black-box model, no claims of causal proof, just a documented statistical relationship applied honestly.

No. Nothing on AllForecasts is investment, legal, or financial advice. Forecasts are probabilistic estimates for informational purposes, built from public data — do your own research before acting on anything you see here.

See for yourself on the Backtest page — every resolved call is listed, hits and misses both, with no cherry-picking. We show calibration, not just a headline hit rate, and flag when the sample size is still too small to draw strong conclusions.

Real public providers only, credited alongside each figure: the World Bank, ONS, WHO, UNESCO, Alpha Vantage, and GDELT, among others. We never invent a number — if we can't source it, we don't publish it.

Yes, entirely free to use, with no account required.

AllForecasts was founded and built by Zarak Khan. Questions, feedback, or issues — email hello@allforecasts.com.

No. No cookies, and no analytics or advertising trackers of any kind. A couple of small conveniences (like a stocks watchlist) are saved only in your own browser's local storage, never sent to us. Full detail is on the Contact page under Policies.

Zeno is AllForecasts' AI assistant — ask it about any prediction, indicator, or correlation on the site and it answers grounded in the site's real data, not invented numbers.

Email hello@allforecasts.com, or see the Contact page for our X and Instagram.