Within CPMAI and PMI’s AI pattern framing, predictive analytics is the pattern that focuses on using historical and real-time data to forecast future states—exactly what is needed for route optimization under changing traffic conditions. For a logistics company, the AI system must estimate future travel times, congestion levels, delays, and likely delivery windows. These predictions are then used as inputs to optimization logic that chooses the best routes and adjusts them dynamically as new data arrives.

Recognition/summarization patterns focus on classification or extracting meaning from content (such as images or text), while conversational patterns are aimed at dialog systems like chatbots. Automation and rule-based systems can encode fixed routing rules, but they cannot by themselves learn patterns from historical traffic and adapt to evolving conditions. PMI/CPMAI guidance highlights that when the business problem involves forecasting outcomes to inform better decisions, the appropriate AI pattern is predictive analytics—often implemented with regression, time-series models, or more advanced learning approaches. Therefore, for optimizing delivery routes while adapting to real-time traffic, the correct pattern is predictive analytics, making option D the appropriate choice.