You are the AI Program Manager for a global logistics company.

Within the CAIPM framework, AI use case identification focuses on aligning business problems with the most appropriate AI capability category. In this scenario, the organization is transitioning from a reactive operational model to a proactive, forecast-driven approach for inventory management.

The key phrase in the question is “analyzes historical sales data and real-time market signals to forecast inventory needs weeks in advance.” This directly corresponds to Predictive Analytics, which uses historical data, statistical models, and machine learning techniques to predict future outcomes. In supply chain and logistics, predictive analytics is commonly used for demand forecasting, inventory optimization, and risk anticipation.

Option A (Process Automation) refers to automating repetitive tasks but does not inherently involve forecasting or future predictions. Option B (Customer Intelligence) focuses on understanding customer behavior, segmentation, or preferences—not operational inventory planning. Option C (Sentiment Analysis) analyzes textual data such as reviews or social media, which is irrelevant to inventory forecasting.

CAIPM emphasizes that high-value AI use cases often shift operations from reactive to proactive decision-making. By forecasting demand in advance, the organization can optimize stock levels, reduce excess inventory, minimize stockouts, and avoid costly emergency logistics such as rush shipping.

Therefore, the correct answer is Predictive Analytics, as it directly enables forward-looking demand planning and strategic inventory optimization.