Data Action Layer December 26, 2018
Alkymi CEO, Harald Collet, spoke at DataDriven NYC, a monthly event covering big data, data-driven products, and startups. The event was hosted by Matt Turck, a FirstMark partner. Harald explained that in the financial services industry, many documents sent via email contain valuable data in the text or attached as a document. To access and use data from these sources requires attention and manual work and resources to identify and extract the necessary components.
Alkymi Data Inbox uses computer vision to identify the basic components of the document, such as tables and charts, and Natural Language Processing (NLP) to understand the intentions of the texts and summarize their content. As a result, Alkymi extracts customer insights from unstructured data and automates manual workflows.
Collet drove home Alkymi’s strengths, including its ability to actively learn and adapt to the company’s data, having a human in the loop when needed, and how its visual approach allows the user to easily trace the results back to the original content. With Alkymi, business analysts do not have to waste their time on mundane work, like sifting through numerous documents, and instead, can focus on more important tasks that better match human expertise.
You can watch the talk here. Or contact Alkymi to learn more.
Fine-tuning is not the only way to get relevant, domain-specific responses out of an LLM. Alkymi’s team of expert data scientists explain an alternate route.
Find out which type of automated document processing solution is right for you: data extraction, an IDP, or a complete business system for unstructured data.
We’re partnering with Portfolio BI, a provider of portfolio analytics and reporting solutions, to bring structured and unstructured data sources together.