1. Give a real-life example where clustering can be applied (preferably but not necessarily in accounting).
2. You read the paper about anomaly detection. Give a real-life example where anomaly detection can be applied in governmental accounting.
3. One of the recorded lectures talks about duplicate payments and how to identify them. Briefly describe the three phases of the duplicate records identification process. Can you think of another kind of records where you might have a similar problem (duplicates) in the public sector? How would you address that issue, i.e. how would you identify those duplicate records?
4. In the paper Continuous Assurance and Text Mining, the authors discussed text mining emails, and more specifically Enrons emails. Briefly explain how text mining emails can be informative, and refer to Enrons example whenever possible. Discuss the major challenges that one might encounter when mining textual data.