This is a recurring event: View all events in the series “Data Bites”
We all know that AI is amazing and applying state-of-the-art algorithms always seems like a good and winning idea.
However, there is a reason why you'd want a fence near a ravine and seat belts on your car. Some say it’s common sense; nonetheless, machine learning models usually don't have that and the results can be disastrous.
This talk is about:
- Successfully designing ML systems to ensure high-quality standards of AI applications
- Celebrating constraints on models to improve performances and reliability
- Integrating ML algorithms and domain knowledge to ensure successful scalable deployment in production environments.
About the Speaker:
Alessandro is the founder and CEO @Pharmadvice. The mission of the Rome-based startup is to enhance key business decisions, monitoring and operations by merging industry knowledge and cutting-edge AI systems.
To accomplish the latter objective, the company developed a business intelligence and anomaly detection system tailored for retail pharmacies.
During Covid, he participated as CTO in a tech startup (U-Ant), that was later sold to an institutional investor. He oversaw the following core activities, serving worldwide clients (10K+ employees and up to € 9B+ in revenues):
- Development of AI/ML algorithms for Covid-19 risk assessment and DNA sequence analysis
- Management, provisioning, and deployment of ML-driven models on cloud infrastructures (AWS)
- KPI tracking and presentation to key stakeholders and clients.
After successfully graduating in Data Science at City University of London, he joined Bain & Company (Milan) as an advanced analytics associate. Main projects included:
- Developing a customer segmentation pipeline, analyzing 50+ GB for the major Italian toll-road operator
- Implementing an ML-driven predictive maintenance solution - turbines and transformers - for the Italian hydroelectric market leader
- Designed a Deep Learning fraud detection algorithm for the Italian market leader in digital payments to improve as-is system performances.
Attendance at City events is subject to our terms and conditions.