---
title: "Classifying claims correspondence | cm-opti case study"
url: https://cm-opti.com/business-cases/insurance-claims-correspondence-classification
description: "An NLP model classifies claims correspondence at an insurer in a GDPR-compliant environment. 25% fewer documents, 90% accuracy, 30% less backlog."
language: en
---

# Classifying claims correspondence at an insurer

**Insurance, regulated industry**

## Industry and type of organization

A mid-sized insurer operating in a heavily regulated environment. Data protection and processing security are a prerequisite for entering that market. The engagement is ongoing.

## Business problem

The customer service team and the document-processing team were working at the limit of their capacity. Every letter entered the queue in the same form, regardless of whether it concerned an urgent case or added nothing new.

Rising handling times began to threaten deadlines, and in claims handling a delay means the risk of a claim becoming time-barred and lower customer satisfaction. The backlog kept growing because the queue grew faster than it could be cleared.

## Approach and scope of work

We designed and deployed an NLP (natural language processing) model that reads incoming correspondence and assesses it on two counts: whether it is relevant to the customer's case and what risk it carries. Letters irrelevant to the case are set aside from the main queue so they do not slow down cases that require a response, and nothing is deleted in the process. The rest are classified and passed on with a ready category, so the next steps of the process can run automatically. Underneath, text classification with supervised learning does the work: the model learns from labeled examples of letters and attaches a confidence level to every decision, so uncertain cases go to a human.

## Business impact

around 25%

fewer documents in handling

the system sets aside correspondence irrelevant to the case

90%

recognition accuracy

correctly identified risk category

30%

smaller backlog

reduction in the old correspondence backlog

About 25% of documents stopped burdening the main queue, because the system sets aside correspondence irrelevant to the case. The risk category is identified correctly in 90% of cases, which lets clear-cut cases be routed automatically and leaves doubtful ones for a human to check. The correspondence backlog dropped by 30%.

## Scale of the implementation

The solution works on hundreds of thousands of documents a year. We maintain and keep developing it, so the model is retrained as the character of incoming correspondence changes.

## Security and confidentiality

We ran the project under a GDPR-compliant regime. The data the model worked and learned on was anonymized, so at no stage was it tied to a specific person.

The whole thing runs in a separate, secured environment built for this project. The architecture was dictated by regulatory requirements: the data does not leave the agreed environment, and every processing step can be demonstrated in an audit. In a regulated industry, this is a precondition for approving a solution for use.

Reviewing documents by hand eats up time that no one budgets for. If it looks similar at your company, [write us a few sentences about your process](https://cm-opti.com/en_index#kontakt). We will tell you whether we see a way to take work off your team, and we will say so if, in our view, there isn't one.

## Related articles in the cm-opti knowledge base

- [What are OCR and NLP](https://cm-opti.com/knowledge-base/what-is-ocr-nlp)
- [What is RAG and an AI agent](https://cm-opti.com/knowledge-base/what-is-rag-ai-agent)
- [What is process automation](https://cm-opti.com/knowledge-base/what-is-business-process-automation)

Service area: [AI process automation](https://cm-opti.com/en_solutions#automatyzacja) (document processing and correspondence classification).

## More case studies

[Project management in construction, German market AI assistant for HOAI and VOB](https://cm-opti.com/business-cases/ai-assistant-hoai-vob-regulations) [Distribution and logistics, multiple markets Demand forecasting and distribution optimization](https://cm-opti.com/business-cases/demand-forecasting-distribution-optimization) [Logistics and freight forwarding (TSL) TMS integration and document capture](https://cm-opti.com/business-cases/tms-integration-document-capture)

[← Back to all case studies](https://cm-opti.com/business-cases/) [Next case → AI assistant for HOAI and VOB](https://cm-opti.com/business-cases/ai-assistant-hoai-vob-regulations)