Forge Empowers Managers with Generative AI & IDP for Efficient Document Processing

Forge Global, Inc. is a leading fintech company that has been democratizing access to private market investments since 2014. The company's pioneer platform provides liquidity solutions for private markets, enabling participants to trade shares in the most prominent pre-IPO companies globally. Leveraging advanced technology, a robust network of relationships, and extensive market expertise, Forge provides clients with efficient, transparent, and fair access to private market transactions. Committed to innovation, Forge adapts its solutions and services to meet clients' needs, shaping the future of private market investing. As a fintech company, Forge relies on document- and data-centric operations. The ability of its employees to quickly and accurately collect, store, process, manage, and leverage massive volumes of documents — and data — that the company’s partners share with Forge is crucial.

Forge Global, Inc., a leading fintech company, was facing challenges in managing and processing large volumes of complex corporate documents. The company's existing manual and semi-automated document processing pipelines were unsustainable due to their lack of speed, cost-efficiency, and scalability. The task of processing clients’ corporate documentation could not be outsourced due to security and compliance concerns. The documents often contained sensitive information and any data extraction process had to comply with privacy laws and regulations. The company's leaders recognized the need for a more advanced and automation-focused solution to expedite the processing of incorporation documents, automatically extract data from them, and generate incorporation reports. They sought to partner with an AI solutions provider and technology consultancy to design and build the desired platform, while maintaining the security and compliance of its document- and data-centric operations.

Provectus, an AWS Premier Consulting Partner, was chosen to deliver the project. The project was divided into several key phases, including the development of a data lake using Amazon S3, the development and implementation of machine learning pipelines using Amazon SageMaker and AWS StepFunctions, the application of various Deep Learning and NLP/NLU algorithms and frameworks for enhanced data extraction, and the utilization of Large Language Models (LLMs) for text understanding and data extraction. Provectus’ Intelligent Document Processing (IDP) solution was used as a foundation for the document processing and report generation platform. During the solution’s customization, Provectus took advantage of industry best practices to enhance platform resilience, refine the infrastructure for increased stability and reliability, strengthen security measures in line with AWS best practices, document both current and future infrastructure and practices used, and improve platform observability and traceability.

• By partnering with Provectus, Forge revolutionized its document-centric operations, unlocking new levels of speed, efficiency, and scalability. The Generative AI capabilities of the delivered document processing and report generation platform empower Forge to automate the routine tasks and enable them to optimize costs while freeing up managers’ time to focus on higher-priority tasks, thus driving productivity and strategic decision-making. By incorporating AI, Forge has successfully modernized its document processing workflows, marking a pivotal step in its journey towards digital and AI transformation. The significant reduction in manual review and preparation of corporate documentation has bolstered throughput rates, demonstrating the immense potential of Generative AI to enhance operational efficiency.

• The platform was delivered in a four-month timeframe

• The initial goal was to develop an automated solution with a human review component, aiming for a review ratio of 95% automation and 5% human review upon completion of ML model training

• The accuracy target for the ML model was set at 70% or higher