The client is a Silicon Valley based tech platform which has become one of the most widely used A.I. legal research technologies in the legal-tech sphere. The company was seeking support on collecting and structuring public data of legal cases from all 50 US states to feed its ML and AI engine and train a superior solution.
A tailored data collection web scraper to collect legal case data from all 50 states, and multiple web resources was developed. The main resolved challenge was to transform non-digitized PDF documents with machine unreadable raw text, into structured well defined and unified format for further machine training and analysis.
The delivered data allowed the client team to develop one of the most sophisticated AI products in the legal market, enabling it to secure wide adoption across the legal market from the largest 'Am Law100' firms to solo practitioners.