The FIRST project provides a large-scale information extraction and integration infrastructure that supports non-ICT skilled end users for on-demand financial information access and execution of financial market analyses. Innovations in FIRST are: information extraction from unreliable semi-structured sources on a massive scale and in near real-time; automatic reuse of existing ontologies, large-scale ontology learning, and advanced decision models making use of semantic attributes.

The FIRST Decision Support Infrastructure enables end-users to configure, deploy, and execute financial decision models with associated information channels. The FIRST Ontology Infrastructure provides tools for semi-automatically creating and maintaining domain knowledge models. The FIRST Semantic Information Extraction System addresses noise, uncertainty, and semantic interpretation of information sources. The FIRST Information Integration Infrastructure consolidates information from very large heterogeneous information sources

FIRST validates its innovations by three complementary use cases of market surveillance, investment management, and online retail banking and brokerage. The consortium comprises for each solution providers, data sources, and end users. FIRST implements a systematic strategy for scaling its methods and software infrastructure to the processing of massive amounts of information in real-time by three steps:

1. functional prototype
2. scaling for non time-critical processing of massive historical data, and
3. scaling for massive live streams of structured feeds, textual news wire feeds, as well as semi-structured Web information in real-time

The impact is ensured through an active open source strategy which

1. bases all basic software components in the fields of ontology learning, information extraction, information integration, and decision support on existing open source software and
2. releases FIRST software as open source software.