Which problem concerns you the most? Document clustering can answer this question using the full-text data from your problem database.

For which topic should capacities be deployed in the next major improvement project? This question is usually decided based on gut feeling or using manually maintained error categories. Maintaining the error categories is not only time-consuming but also highly error-prone and imprecise.

With document clustering, the most common topics can be identified directly based on word frequencies and collocations from the full-text data. This is less time-consuming and more accurate than error categories.

We will show how document clustering can be used to identify the top topics.