We are drowning in data and starving for information. There are potentially invaluable knowledge and undiscovered relationships hidden in the data already stored in the PI System. The complexity and volume of data makes it formidable for naked eye or classic tools to discover and extract such multivariate relationships. In this presentation we show how we can perform machine learning algorithms on PI System data. In two separate scenarios we will focus on integrating the PI System with SQL Server Analysis Services and MATLAB and show examples of implementing machine learning algorithms, training and performing predictions. he resulting models could be used in predictive analytics use cases such as price forecasting and preemptive maintenance.