Presentation is loading. Please wait.

Presentation is loading. Please wait.

BI09 – Cortana Analytics and Power BI

Similar presentations


Presentation on theme: "BI09 – Cortana Analytics and Power BI"— Presentation transcript:

1 BI09 – Cortana Analytics and Power BI
Brandon George, Hillstar Business Intelligence

2 agenda Cortana Analytics Overview Perspectives of Data
Suite Overview Machine Learning API’s Integration with Power BI Perspectives of Data Past, Present and Future BI Maturity Scale From past to future Example Customer Case Customer overview Business Outcomes Inventory Insights OTIF Improvements Production predictive insights Cortana Analytics Process (CAP) CAP Overview Process steps Azure Machine Learning Studio Azure ML Studio Overview Explore Twitter Sentiment analysis Power BI Quick Insights Review of Power BI Quick Insights Q&A Power BI Pro, Resources and more!

3 The only thing that gives an organization a competitive edge...is what it knows, how it uses what it knows and how fast it can know something. - Larry Prusak (1996) Larry Prusak: researcher and consultant, founder and Executive Director of the Institute for Knowledge Management (IKM). IKM: a global consortium of member organizations engaged in advancing the practice of knowledge management through action research. Larry has had extensive experience, within the U.S. and internationally, in helping organizations work with their information and knowledge resources. He has also consulted with many U.S. and overseas government agencies and international organizations (NGO's). He is currently on the faculty of Columbia University teaching in their Information and Knowledge Strategy Program

4 Cortana Analytics Overview

5

6 Azure Machine Learning API’s
Customer Churn Prediction Face API Speech API Vision API Anomaly Detection Product Recommendations Basket Analysis Text Analytics

7 Cortana and Power BI Developers can use the Power BI API to programmatically send data sets to Power BI. This includes from streaming analytics with event hubs and further from Machine Learning and Azure SQL Databases.

8 Three perspectives of Data

9 Three perspectives of data

10 BI Maturity Scale

11 From Past to Future Reactive Proactive Historical data Predictive
People and processes Automatic decisions Data is pervasive, yet insights are elusive. According to Gartner, more than 85 percent of the data available to organizations is automatically generated – from every device, sensor, upload, tweet, purchase, shipment and keystroke. Yet many organizations experience challenges as they try to draw actionable insights from a world of big data… Reactively seeking small patterns and insights from data, and then having the ability to act on it. Shifting from the analysis of what happened in the past to predicting what might happen in the future  the key to shaping new business outcomes. And ultimately moving from manual, people-heavy decision making to automated machine-assisted decisions that accelerate business and aid competitive advantage.

12 Example Customer case

13 Customer Overview Multinational Large Plastics Manufacturer
15k+ Employees Worldwide 100+ sites around the world AX 2012 R2 deployed fully

14 Business Outcomes Improve On Time in Full (OTIF) to 99%+
Reduce overall stock levels Improve production plans

15 Inventory Insights Coloration between stock, produced and delivered qty’s. Reveals direct insights of OTIF per period over all stock Suggestions based on predicted growth / reduction of stock level for forward planning.

16 Inventory Insights Show total stock of an item against Ordered / Delivered Qty’s. Red shows predicted days that will miss delivery perf. Green shows inventory delivery demands.

17 Production Predictive Insights
Predictions on item and resource consumption for stock levels. Showcases predicted probability.

18 Cortana Analytics Process (CAP)

19 CAP Overview Plan Analytics targets and project focus
Prepare Analytics Environment Data Features Model

20 CAP Process Steps

21 Azure machine learning studio

22 Azure ML Studio Studio.AzureML.net
Workflow focused predictive model creation. R is a huge focus

23 AzureML: Twitter sentiment
Read data Pre-process events 80/20 split Feature selection Train Score Evaluate

24 Power BI Quick Insights

25 Power BI Quick Insights
Demo: Launch quick insights Review within PowerBi.com Show how to add to existing dashboard Natural Query Language.

26 Contact information Brandon George Hillstar

27 Final reminders CPE Credit Code: 53C2 Complete Surveys

28


Download ppt "BI09 – Cortana Analytics and Power BI"

Similar presentations


Ads by Google