Harnessing the power of AI on streaming data generated by thousands of IoT devices is no easy task. Lennox International came to this realization as they looked to build a smarter HVAC system by analyzing large data sets, combined with external data sources such as weather data, and predicting equipment failure with high levels of accuracy along with their influencing patterns and parameters.
Join this latest Data Science Central webinar to learn how Lennox leveraged Azure Databricks and PySpark to solve their biggest data challenges and improve data science and engineering productivity, resulting in complex machine learning models that run in 40 minutes with minimal tuning and predict failures with accuracy of about 90%.
This webinar will cover:
– The data orchestration challenges Lennox faced which impacted model accuracy levels and data processing times
– How they use Azure Databricks to build the data engineering pipelines, appropriate machine learning models and extract predictions using PySpark
– How they also implemented stacking, ensemble methods using H2O driverless AI and Sparkling -Water on Azure Databricks clusters, which can scale up to 1000 cores
Speakers:
Prasad Chandravihar, Lead Data Scientist — Lennox International
Deepsha Menghani, Product Marketing — Microsoft
Hosted by:
Bill Vorhies, Editorial Director — Data Science Central
