Satellite telemetry data management and analysis present unique challenges due to the high volume and complexity of data. This project aims to develop an efficient system to correlate satellite command to Parametric Identification (PID) using hybrid machine learning (ML) techniques, including the Auto ARIMA model for change detection. By integrating Auto ARIMA, the system can automatically detect shifts in command to PID correlations, enhancing satellite health monitoring, anomaly detection, and command verification. The study utilizes advanced data processing techniques, multiprocessing, and multithreading to handle large datasets and develop robust ML models for real-time monitoring and command-PID correlation. This approach ultimately improves operational efficiency and reduces the manual workload.