Case Study: MTEC achieves faster, more accurate PDF text extraction with Adobe PDF Extract API

MTEC uses Adobe PDF Extract API to improve speed and accuracy of automatic text extraction from financial data PDF files

MTEC, a Tokyo-based financial data science and consulting institute, needed a faster and more accurate way to extract text from PDF reports used in ESG and financial analysis. Its older tools often broke sentence structure at awkward line breaks, making it difficult to preserve meaning in integrated reports and other document-heavy sources. MTEC turned to Adobe, using Adobe PDF Extract API and Adobe Acrobat Services to address the challenge.

With Adobe PDF Extract API, MTEC automated PDF text extraction while preserving headings, body text, and sentence structure, outputting results as JSON for easier analysis. The solution significantly sped up its analysis and verification cycle, improved extraction accuracy, and reduced manual cleanup work, enabling more reliable surveys and broader use across integrated reports, TDnet disclosures, and other reports from thousands of listed companies.

MTEC

Yusuke Naritomi

Financial Engineer