Kensho Extract is Now Available on S&P Global Marketplace
We’re thrilled to announce that Kensho Extract is now available on the S&P Global Marketplace.
S&P Global Marketplace is a site that enables users to easily find datasets and machine-enabled solutions from across S&P Global. The inclusion of Extract underscores the growing importance of Kensho’s technology in the financial services industry.
Tarig Khairalla, Product Manager of Kensho Extract talked about why he’s excited about seeing Extract on Marketplace: couldn’t be more enthused about this announcement. He said, “Our clients are sitting on piles of crucial information that are all stuck in PDF files. Extract is an efficient and fast way for us to enable them to gain value with a solution that can be flexible integrate with workflows. It’s a big win for us that Kensho products are unified under the S&P Global Marketplace, which makes Extract and our competitive AI technology accessible to all our clients.”
Kensho Extract is a fundamental machine learning (ML) capability that allows users to access both text and tables in a simple-to-use format for further analysis and action. Extract’s advanced algorithms are capable of understanding and processing text from sources such as news articles, research reports, and regulatory filings, providing clients with actionable insights in real time. Utilizing sophisticated ML models, Extract converts complex PDF documents into easy-to-use machine-readable formats.
Extract can be used independently or in conjunction with other services offered by Kensho. With Extract, users can:
- Quickly transform unstructured documents into a machine-readable format that organizes the headers, titles, paragraphs, tables and footers detected within the document in natural reading order.
- Interpret messy page layouts, structuring text into cohesive paragraphs that can then be effectively analyzed and searched.
- Augment their human workforce with easy-to-use document extraction tools, including a browser-accessible user interface.
An Extract Use Case: Table Extraction at Scale
Many document viewing providers serving researchers and knowledge workers provide millions of financial and business documents to their users. These documents have complicated layouts and come in PDF formats. These providers need to allow their users to extract and export tabular information for their downstream analysis and needs.
Many existing solutions today fail to accurately accomplish three things:
- Identify where tables are in a given document.
- Accurately extract the necessary information from those documents.
- At scale, provide a high level of performance in terms of SLA. This leads to poor user experience and ultimately a reduction of user retention from these platforms.
Kensho Extract is able to structure a document very quickly. Its state-of-the-art model outperforms many leading competitors in the market in processing time. Its document structuring allows users to find the titles, tables and paragraphs within a document and its table and text extraction features allow users to export desired pieces of content from within documents.
Interested in learning more about Kensho Extract? Contact us to set up a meeting or to have your questions answered.
