A support ticket records a customer request, problem, inquiry, or suggestion for service handling. Teams triage tickets by priority and type, then assign them for resolution. section 8.2.2
Automated categorization can use simple keyword rules or supervised classification. Business patterns can guide the design, but untested rules and biased training data may produce inaccurate or unequal outcomes. section 8.2.2
A ticket workflow can classify:
- Priority as Low, Medium, or High to determine queue order and response urgency. section 8.2.2
- Type as Product Problems, Delivery, Billing, Inquiries, or Suggestions. section 8.2.2
- Patterns such as keyword coverage and seasonal changes in ticket volume. section 8.2.2
Figure 8.4 An automated system for categorizing data can employ anything from simple rules to sophisticated machine learning algorithms.
Compare rule-based and machine-learning approaches to automated ticket categorization. section 8.2.2
Figure 8.5 The categorization system developed by the data science and analytics team can streamline the work of the customer support team. Still, it may have an unanticipated negative effect on certain groups of customers.
Consider how streamlined categorization might create unanticipated negative effects for particular customer groups. section 8.2.2
