Real-World Azure Machine Learning at EF Education First by Stefano Tempesta

In this session, Stefano gives an overview about the Power of Azure Machine Learning (ML) and how they use ML at “EF Education First” to drive their business forward.

Speaker: Stefano Tempesta, EF Education First
Stefano is the Vice President of Engineering at EF Education First (http://www.efswiss.ch/de/), the world’s leading private international education company. He is a regular speaker at conferences, including Microsoft Ignite, TechEd, NDC, API World and the European SharePoint Conference. Stefano’s interests span across Cloud, Mobile and IoT applications. You can reach him via his personal web site http://www.tempesta.space/.

Transcript

1. COGNITIVE SERVICES MACHINE LEARNING CORTANA INTELLIGENCE BOT FRAMEWORK
2. TOPICS Online Payment Fraud Detection Intranet Sentiment Analysis Cache Hit Ratio  Improved Page Load Time Emergency Response
3. VISA handles 2000 transactions / sec = >172M tpd PayPal handles = >135M tpd In 2015, financial fraud totaled a cost of € 900 million
4. Traditional Payment Fraud Detection Analyze transactions and human-review suspicious ones Use a combination of data, horizon-scanning and “gut-feel” Every attempted purchase that raises an alert is either declined or reviewed ▪ False positive ▪ Fail to predict unware threats ▪ Need to update risk score regularly
5. ML Payment Fraud Detection Large, historical datasets across many clients and industries ▪ Benefit also small companies Self-learning models not determined by a fraud analyst ▪ Update risk score quickly
6. Sentiment Analysis “Sentiment Analysis is the process of detecting whether a piece of writing is positive, negative or neutral” ▪ ML-driven Text Mining ▪ Opinion Polarity
7. Text Analytics Applications: ▪ Product Reviews ▪ Case / Document Classification ▪ Social Media Analytics ▪ Intellectual Property ▪ Plagiarism Check
8. Text Analytics API Analyze unstructured text for tasks • Language detection • Key phrase extraction • Sentiment analysis Returns a numeric score between 0 and 1 ▪ Negative 0 .. 1 Positive sentiment Advanced natural language processing https://azure.microsoft.com/en-us/services/cognitive-services/text-analytics/
10. 10 Two-level Cache
11. Emergency Response