DocQMiner: contract analysis through AI

Case study

DocQMiner: document analysis through AI

The cost effective, quality focused and faster way to retrieve data points from unstructured documents

80% of all company data is unstructured and grows much faster in size than its structured counterpart. Unstructured documents contain often valuable insights but it is laborious and mind-numbing to extract these insights, especially for large volumes of documents in various formats and languages.

Your challenge

One of these areas is complying with international regulations. For example, companies with lease contracts are required to go through thousands of contracts one by one. It’s an immense task, certainly when you consider that more than 100.000 contracts and analysts spending around 90 minutes on each contract.

DocQMiner One-Pager

Challenges of getting data out of large volumes of unstructured documents

  • Time consuming - Finding data points in long documents is time consuming. Experts are wasting time browsing and searching instead of what they are trained for.
  • Mind-numbing - Document review and data point retrieval often require involvement of experts even though this is a mind-numbing task. Typically 60-80% of the work is simple and repetitive and only exceptions require time of experts.
  • Many formats & languages - International companies must deal with many different types of documents making it hard to standardize. Multiple languages makes it even harder to organize your workforce effectively.
  • Always urgent - New regulations and mandatory regulatory remediation efforts require you to go back to documents to obtain additional information.
  • Hard to assess quality - Manually sifting through thousands of documents is error prone. And once you’ve got the data it is still difficult to prove data is reliable and can be trusted
  • Expensive - Large volumes require you to mobilize a large workforce and support organization. How can you minimize cost and still benefit from all the insight locked away in these documents?

Our solution

To assist companies with challenges like these, Deloitte has developed DocQMiner: a self-learning application that reads through and analyzes documents. It works in a loop in which human expertise is enhanced by suggestions from the AI. Once documents are analyzed and reviewed the AI-engine learns by example becoming more accurate in its suggestions with every processed document.

This approach accelerate data processing as well as other significant business benefits;

  • Saves time: Reduces the processing time 50-70%
  • Value added: Experts focus on meaningful work instead of mind-numbing work
  • Flexible: Flexible data retrieval and supports 140+ languages
  • Designed to scale: To any geographies and team size allowing you to quickly sift through piles of documents
  • Improves quality: Through reliable review process with track & trace
  • Cost effective: By minimizing human effort so allows you to reduce cost and meet deadlines

DocQMiner- contract analysis through AI

*) This case is part of the series of 16 Artificial Intelligence projects from Deloitte. Other cases in the series are in random order:

  1. TAX-I: A virtual legal research assistant
  2. AI Benchmark 
  3. SONAR: Find labelling errors in databases
  4. Transaction detector with regard to the Dutch work cost regulations
  5. GRAPA: assistance with risk strategies
  6. Chatbot as a handy search tool for the online technical library
  7. Argus: an eye for detail
  8. PostNL: optimising delivery times
  9. Virtual assistants: beyond the hype
  10. HR agent Edgy: the future of Human Resources
  11. Using machine learning to assess risks for insurance policies
  12. Predicting payment behaviour
  13. DocQMiner: contract analysis performed in no time at all
  14. Combating welfare fraud with machine learning
  15. Using machine learning and network analytics to search for a needle in a haystack
  16. Clustering unstructured information in BrainSpace

Sign up for the email alert to get all cases through email.

Vond u dit nuttig?