LG AI Research and London Stock Exchange Group have launched an AI-powered, explainable equity forecast score system for all 5,500 US-listed stocks, expanding coverage beyond just large-cap names.

Future plans include tailored solutions for brokers and quantitative investors, with cross-market learning to boost forecasting accuracy as markets become more interconnected.

The solution rolled out in January via a subscription model through LSEG, targeting LSEG’s 44,000 financial clients and integrating into its data platform.

Explainability is central, with rationale and factors behind every forecast to address concerns about black-box AI in finance.

The platform uses LG’s Exaone foundation model to process structured data (prices, earnings, macro indicators) and unstructured data (news, filings), delivering daily forecasts with scores from 1 to 100.

US outreach is underway with early interest coming from Europe, South Korea, Japan, Thailand, and parts of the Middle East, with plans to expand beyond US equities to the Korean market and other asset classes.

Forecast scores above 50 suggest potential upside over a four-week horizon, while scores below 50 indicate downside risk, accompanied by narrative explanations for transparency.

LG frames this as a shift from selective stock coverage to daily, market-wide intelligence, with human analysts remaining essential but AI expanding the research frontier.

LG has already deployed related products, including the LG QRAFT AI-Powered US Large Cap Core ETF, which outperformed its benchmark by 600 basis points from August 2024 to August 2025.