Formula Insight

Formula Insight (YC S24) is launching its new equity research platform. Integrated with FactSet data and designed by a former Citadel investor and SpaceX engineer, it's built to enhance the core workflows of institutional equity investors. Institutional investors use spreadsheets to manage billions of dollars for investments. However, key insights are lost when connecting the dots between complex Excel financial models with millions of cells and across hundreds of SEC filings, management transcripts, and research papers. Formula Insight expedites the research process by analyzing these critical documents in minutes, helping investors gain an edge in the public markets. Congrats on the launch, Will Tong and Stefan Raghavan! https://lnkd.in/gz5fJDA5

🚀 Formula Insight launched! Search & Analyze Complex Spreadsheets Using Plain English "A central repository for hedge funds to store their most valuable Excel data, accessible through conversational search." 🌐 www.formulainsight.io 🛠️ Powered by an API that converts raw Excel files into structured, labeled data, capturing semantic context for every cell ⚡ Makes complex spreadsheets searchable, expediting analysis for hedge funds 🧠 Founded by former Citadel and SpaceX professionals Congrats Will Tong & Stefan Raghavan!! https://lnkd.in/gCxsiciP

⁉ For financial professionals, the latest advances in GenAI do not offer the same added value as for IT, legal and media experts. Why? Because while large Gen-AI models are excellent at handling text, images and sound, financial data is mainly number-based and does not have a standardized syntax like program code. Each company has its own cost and revenue structure that requires individual logic and presentation. The MS365 Copilot for Excel clearly demonstrates this challenge: when dealing with data, it is not as effective as its counterparts for emails, documents or meetings. 📄 A recent and fascinating paper from Microsoft introduces the “SpreadsheetLLM”, which converts spreadsheet content into a new format that LLMs can work better with. The aim is to answer questions about Excel spreadsheets, manipulate data and even create new spreadsheets using natural language input. 🚀 The startup Formula Insight takes a similarly interesting approach. They are building an API LLM interface that lists each cell of the Excel spreadsheet in a JSON file with all its properties. In this way, the spreadsheet becomes searchable for LLM. The range of tools currently available to make the day-to-day work of financial experts easier is still very limited. 💡 We at DocuTrust have recognized precisely this problem and are working on a technology that understands financial data and the underlying relationships.  🎯 “Financial Table Understanding” is one of the core problems we are working on. Stay tuned for the innovations we will be presenting to you soon!

Formula Insight (YC S24) makes complex spreadsheets searchable in plain English, expediting analysis for hedge funds. Excel data is critical to any hedge fund's investment process. However, it’s inefficient to extract and compare details between various complex models. Built by Stefan Raghavan and Will Tong, Formula Insight can label and store every single cell in a central repository. Modeling variables can be easily extracted and compared using natural language. Eventually, this builds into a knowledge database for the next generation. Congrats on the launch, Stefan and Will! 🚀 https://lnkd.in/gqyuxnkj

Formula Insight (YC S24) makes complex spreadsheets searchable in plain English, expediting analysis for hedge funds. Excel data is critical to any hedge fund's investment process. However, it’s inefficient to extract and compare details between various complex models. Built by Stefan Raghavan and Will Tong, Formula Insight can label and store every single cell in a central repository. Modeling variables can be easily extracted and compared using natural language. Eventually, this builds into a knowledge database for the next generation. Congrats on the launch, Stefan and Will! 🚀 https://lnkd.in/gqyuxnkj