Real-time Analytics · Risk Management
LG AI Research needed to extend AI systems built for high-stakes manufacturing into financial market workflows where forecasting accuracy alone was insufficient; investors also needed narrative reasoning, governance, and explainability across structured and unstructured inputs before they could trust and act on model outputs.
Reported impact
LG AI Research turned its manufacturing AI foundation into a commercial financial AI offering that delivers both forward-looking equity predictions and natural-language rationale, enabling institutional investors to interrogate forecasts with greater transparency and governance.
LG AI Research adapted the reliability and explainability practices it developed for manufacturing forecasting to a financial-market intelligence stack centered on its in-house large language model EXAONE. The implementation combines structured time-series signals with unstructured news, disclosures, and research so the system can forecast and explain results in analyst-like language rather than emitting scores alone. EXAONE Business Intelligence operates as a multi-agent system that curates new information, forecasts economic prospects, generates equity analysis, and evaluates decision scenarios. Those outputs are then processed into the AI-Powered Equity Forecast Score, which serves institutional investors with a daily equity score and accompanying rationale over a four-week horizon. LG also validated the approach in the LQAI ETF with Qraft Technologies, using natural-language explanations alongside stock ranking and periodic rebalancing.
Structured time-series signals and unstructured news and disclosures are ingested into EXAONE-based processing, where EXAONE Business Intelligence curates the text inputs, combines them with forecasting signals, generates equity analysis and scenario evaluations, and converts the results into the AI-Powered Equity Forecast Score and commentary consumed by institutional investors.
"It provides both a daily equity score and AI-powered rationale (Commentary) for publicly traded US companies across a 4-week horizon."
"LG AI Research leveraged its in-house large language model EXAONE, to interpret unstructured news and combine it with structured time-series signals"
"The multi-agent system curates new and disclosures, forecasts economic prospects, generates equity analysis, and evaluates decision scenarios."
"These outputs are processed into the AI-Powered Equity Forecast Score, now available to institutional investors globally."
"the launch of the LQAI ETF, a public testbed where AI ranks a US large-cap universe, selects 100 stocks, rebalances every four weeks, and explains its rationale in natural language."
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
The LOCATION section lists 한국 D&O 강서사옥 and 서울시 강서구 마곡중앙로 150.
Related
In-house Sample Oct 9, 2026 BBVA BBVA's trading desk needs to respond to institutional client requests for bond, interest-rate swap, and foreign-exchange quotes within milliseconds while balancing competitiveness, profitability, portfolio risk, and… within milliseconds Atalaya · Bloomberg · Viriato 
Google Cloud Sample Archived · Sep 25, 2026 Aldecis Aldecis needed to automate bottom-up financial analysis because CFO and FP&A teams were spending days hunting through dashboards to find the operational causes of margin and profit drift. 85% faster financial data analysis with BigQuery · BigQuery ML · Cloud Run 
Databricks Sample Jul 28, 2026 OpenAI OpenAI’s data platform powers one of the fastest-scaling products in tech history. ChatGPT, the OpenAI API, and the internal tools used by thousands of OpenAI employees require a foundation that can withstand sudden… $400K/month Storage costs eliminated by marketing team Databricks Data Warehouses · Databricks Jobs · Databricks SQL 