Best Practices for Enriching your Data: Combining Microsoft Power BI & Azure AI for Optimal Results скачать в хорошем качестве

Best Practices for Enriching your Data: Combining Microsoft Power BI & Azure AI for Optimal Results

Best Practices for Enriching Your Data: Combining Microsoft PowerBI and Azure AI for Optimum Results | Eastern Analytics Webinar Join Scott Pietroski, Managing Partner and Senior Solution Architect at Eastern Analytics, for a comprehensive guide to enriching your data using Microsoft PowerBI and Azure AI. With over 25 years of experience building analytic platforms for corporations like Bose, Adidas, and Estée Lauder, Scott breaks down Azure ML versus PowerBI ML, covering pros and cons, cost considerations, and best practices for each environment. --------------------------------------------------------------------------------------------------------------------------------------------------------------- Chapters Introduction & Overview 0:00 - 0:41 - Introduction to Eastern Analytics 0:42 - 0:59 - Presenter Introduction (Scott Pietroski, Managing Partner) 1:00 - 1:48 - Agenda Overview PowerBI Desktop & Service Overview 1:49 - 2:27 - PowerBI Desktop Introduction 2:28 - 2:52 - PowerBI Desktop Power Query and AI Insights 2:53 - 3:18 - PowerBI Service Introduction 3:19 - 4:03 - PowerBI Premium Service and Data Flows AI/ML Integration in PowerBI 4:04 - 4:31 - AI/ML Integration Overview 4:32 - 5:21 - Azure Cognitive Services - Text Analytics 5:22 - 6:11 - Azure Cognitive Services - Vision (Image Recognition) 6:12 - 7:00 - Consuming Azure ML Models in PowerBI Desktop 7:01 - 8:03 - Consuming ML Models in PowerBI Service Azure ML Overview 8:04 - 9:10 - What is Azure ML? 9:11 - 10:02 - Azure ML Platform Interface Demo 10:03 - 11:22 - AutoML Functionality Explained PowerBI ML Overview 11:23 - 12:05 - PowerBI ML Introduction 12:06 - 13:44 - PowerBI ML AutoML Wizard Demo Azure ML vs PowerBI ML - Pros and Cons 13:45 - 15:05 - Azure ML Pros (Data Enrichment Platform Example) 15:06 - 15:56 - Azure ML Cons 15:57 - 16:28 - PowerBI ML Pros 16:29 - 17:55 - PowerBI ML Cons Cost Considerations 17:56 - 19:30 - Azure ML Cost Breakdown 19:31 - 20:27 - PowerBI ML Cost Breakdown Technical Comparison 20:28 - 22:12 - Azure ML Technical Side (Platform as a Service) 22:13 - 22:45 - Azure ML Components in Azure Portal 22:46 - 23:47 - PowerBI ML Technical Limitations Data Preparation Best Practices 23:48 - 25:12 - General Data Prep Principles 25:13 - 26:32 - Azure ML Best Practices 26:33 - 27:35 - PowerBI ML Best Practices (Data Consistency) 27:36 - 28:30 - Cognitive Services Cost Management Moving into Production 28:31 - 29:56 - Azure ML Production Deployment 29:57 - 30:33 - PowerBI ML Production Deployment Q&A Session 30:34 - 31:27 - Q: Separate Dev and Production Box for Azure ML? 31:28 - 32:25 - Q: Recommendations for Keeping Azure ML Costs Low? 32:26 - 33:41 - Q: How to Keep ML Models Up to Date? 33:42 - 35:27 - Q: Performance Issues During Data Retrieval? 35:28 - 36:08 - Q: Have You Run Into Times Where ML Doesn't Work? 36:09 - 37:24 - Closing Remarks and Upcoming Building Blocks Series