Charis is a Principal Data Scientist on Autodesk’s BIM360 team. He has applied analytics/AI in healthcare, computational advertising, online gaming, financial fraud detection, and financial scoring. He has also utilized multi-agent infrastructure and related assistive technologies to support human-robotic collaboration for NASA Planetary Exploration missions. His academic background is in economics, public policy, information sciences, machine learning, artificial intelligence, and statistics.
Autodesk is a leader in architecture, engineering and construction software. Autodesk’s BIM360 suite of cloud products for construction enables almost anytime, anywhere access to project-related data throughout the building construction lifecycle. It empowers those in the field to better anticipate and act, and those in the back office to optimize and manage all aspects of construction performance. In this talk we will share how we leverage machine learning to empower proactive construction risk management. These multi-modal applications coupled with external data collection points (e.g. sensors, drones) generate diverse data hosted by different underlying solutions. Generating insights and applying machine learning out of heterogeneous data with regards to data velocity, volume, variety, and veracity within multiple technology stacks is a big challenge. Spark enables managing our growing data heterogeneity in a scalable manner while being able to accommodate both streaming and batch mode data loads. Spark further enables our data science team to work more efficiently, reduces model-to-production conversion cycle, and facilitates the interplay between data management, machine learning, and insight generation to empower intelligent construction.