What metrics should you consider when evaluating the performance of a model in production?

When evaluating model performance in production, key metrics to consider include accuracy, precision, recall, F1 score, and AUC-ROC for classification tasks; and RMSE, MAE, or R² for regression tasks. Additionally, monitoring latency, throughput, and resource utilization gives insight into model efficiency. It's also critical to track business-oriented metrics, such as conversion rates or revenue impact, as they link model performance back to organizational goals.