Home / Insights / Forecasting and market intelligence
Research topic
A forecast is worth something when it is stated before the outcome exists and scored against what happened. That standard sets how probability forecasts are scored, how a forecast is compared with simple baselines and how a backtest keeps out information from the future.
The research here covers the methods behind that standard and what published studies show about language models and markets as forecasters. Each article cites public, dated sources a reader can check.
Research report
Rillor tested whether CME WTI futures lead an on-chain crude perpetual. The lead held out of sample; no net edge after execution costs reached statistical significance.
Rillor builds agentic forecasting systems that read market data, news and filings. Each forecast is time-stamped and stored with its inputs, model version and rationale before the outcome is known. When the outcome arrives it is added to the record, and the forecast is scored out of sample against baselines. We build the same pipeline on your questions and your data, along with market-intelligence agents that follow the sources you choose and cite where each point came from.
Rillor is not a registered investment adviser or commodity trading advisor and does not provide investment or trading advice. Research, forecasts, data and software described on this site are for research and engineering use. Nothing here is an offer or recommendation to buy or sell any security, commodity interest or digital asset. Past or simulated results do not indicate future results.
AI outputs can be wrong. Important decisions should include human review.
Send the question you want forecast, its horizon and the data you already hold.