Global asset manager Schroders and Artificial Intelligence (AI) firm Nexus FrontierTech have announced the successful development of a proof-of-concept (POC) for a data parsing and extraction solution that achieved over 97% extraction accuracy.
The POC is the first step in developing and integrating an AI solution that will help Schroders’ fund accounting to accurately complete reporting validation checks in half the current timeframe.
“Asset managers are now more than ever depending on machine learning and AI technologies to stay competitive,” said Nexus FrontierTech chief operating officer, Derrick Liao, in a statement.
The collaboration between the two parties started in March 2021 on the Infocomm Media Development Authority’s Open Innovation Platform, hosted by Investment Management Association of Singapore’s Digital Accelerator Programme.
As a firm that provides a range of wealth management services for institutions and individuals, Schroders sought to address problems of highly manual data extraction workflows and gaps in data coverage faced by many of Schroders’ business divisions, including its fund accounting team.
“Next-gen natural language procession (NLP) as a service is fuelled by the demands of accessible AI models to quickly and accurately extract and process complex data that was previously impossible or extremely labour-intensive,” Chwee Kan Chua, global head of operations innovation, Schroders said in a statement.
Nexus, an AI software and systems development firm that automates and accelerates business processes involving large amounts of fragmented and unstructured data, proposed the creation of a custom-built, industry-specific data parsing and extraction solution.
Using a combination of multi-step engineering method combining computer vision and machine learning techniques, traditional optical character recognition (OCR), and financial-industry specific NLP to detect domain-specific content, the POC aimed to achieve three main objectives.
First, complete data extraction coverage of the three main tables that the Schroders’ fund accounting team uses in their validation checks: portfolio statement, statement of total return, and balance sheet; second, deliver an output accuracy of 80-85%; and third, develop a model that is scalable for production use.
The timeframe of the POC build was just over 3 months, beginning in early September and successfully completed in December. Results far exceeded expectations, with Nexus’s intelligent document processing model.
