Maintaining the right inventory of critical parts is essential for ensuring utility reliability and controlling costs. Yet many utilities struggle with manual inventory management, leading to overstocking, stockouts, and inefficiencies.

In this session, Austin Energy shares how its Data Office implemented a machine learning solution within MAXIMO, using SAS and Python to forecast demand and automate reorder processes. The solution analyzes historical consumption trends, predicts optimal inventory levels, and provides real-time reorder alerts—enabling smarter procurement decisions aligned with broader operational goals.

You’ll gain a practical look at the model development process, including feature engineering, system integration, and lessons learned from deploying advanced analytics inside a legacy enterprise system.