Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
SlideShare a Scribd company logo

MACHINE LEARNING – THE WHY, WHAT AND HOW

•Download as PPTX, PDF•
•
SAS in Deutschland, Österreich und der Schweiz
SAS in Deutschland, Österreich und der Schweiz

Introduction into Machine Learning by Dr. Andreas Becks, Head of Pre-Sales Insurance SAS DACH @becks_andreas https://www.linkedin.com/in/andreasbecks/

1 of 12
Copyright © SAS Institute Inc. All rights reserved. MACHINE LEARNING – THE WHY, WHAT, AND HOW Dr. Andreas Becks, SAS @becks_andreas
Copyright © SAS Institute Inc. All rights reserved. Maschine Learning – An Example Everybody uses machine learning today – in your photo app it identifies faces and persons on your images.
Copyright © SAS Institute Inc. All rights reserved. Cheap Compute Power and Parallel Processing “2.5 Exabytes of data are produced every day – that’s 90 years of HD videos.” “90 % of the worlds data today has been created in the last 2 years alone.” March 2015, DN Capital Availability of Data R&D on Algorithms Machine Learning – Why is ML so HOT? Three combining trends: big data, massive compute power, and better algorithms.
Copyright © SAS Institute Inc. All rights reserved. Cognitive Computing Artificial Intelligence Machine Learning Neural Networks Deep Learning There is a lot of buzz around some related terms. Often confused, are they neither separted nor the same.
Copyright © SAS Institute Inc. All rights reserved. Supervised Learning 10 Algorithms Machine Learning Engineers Need to Know Two major groups of algorithms form a set of machine learning tools. Source: KDnuggets based on Udacity’s Intro to Machine Learning Unsupervised Learning Naïve Bayes Classific. Linear Regression Logistic Regression Decision Tree Support Vector MachinesEnsemble Methods Unsupervised Learning Principal Component Analysis Cluster Algorithms Singular Value Decompo- sition Indepen- dent Component Analysis
Copyright © SAS Institute Inc. All rights reserved. The Principle: Recognizing Activities Learning dependent patterns of movements Different sports, different movements –algorithms learns characteristic patterns in sensor data.
Copyright © SAS Institute Inc. All rights reserved. Learning dependent patterns of movements X-Wrist X - Ankle Motion Trajectories Raw data by motion and inertial sensors X-Wrist True Activity Labels X - Ankle Training data: movement in context Machine Learning Support Vector Machines Neural Networks Learned classification The Principle: Recognizing Activities Combination of algorithms clusters the different raw data and connects it to different activties. Doing that, new and previously unknown incoming data can be appropriately classified.
Copyright © SAS Institute Inc. All rights reserved. Use Cases for Machine Learning Manufacturing • Predictive Maintenance • Warranty reserve estimation • Propensity to buy • Demand forecasting • Telematics Healthcare • Alerts and diagnostics from real- time patient data • Risk stratification • Proactive health management Retail • Predictive inventory planning • Recommendation engines • Upsell and cross-channel marketing • Market segmentation • ROI and customer value Travel and Hospitality • Aircraft scheduling • Dynamic pricing • Consumer feedback (social media analysis) • Customer complaint resolution Energy • Smart grid management • Power usage analytics • Energy demand and supply optimization • Seismic data analysis • Carbon emission and trading Sources: Forbes Magazine, July 2016, Harvard Business Review, February 2016 Financial Services • Risk analytics and regulation • Customer segmentation • Cross-/Up-Sell • Campaign management • Credit worthiness evaluation More than a third of early movers also saw gains in bottom-line performance using machine-reengineering to slash 15% to 70% of costs from certain processes. Business processes in every industry will be affected.
Copyright © SAS Institute Inc. All rights reserved. Example: Predict Maintenance of Computer Tomographs Thousands of devices, Tens of thousands event codes per day, sensor data 1,000s of predictive models Challenge: Predict failures of components 5 to 10 days in advance >70% precision and <20% false positives Impact on operative processes Real applications tend to become complex. It‘s not only 1 model / algorithm!
Copyright © SAS Institute Inc. All rights reserved. Managing the Analytical Life Cycle Only integration of best models into business processes generates value Discover Deploy Prepare data Explore Model Integrate into business processes Execute Evaluate Ask IT, Business Analyst, LoB Robust Automation Actions Decisions Operations Experiments Data Science New data Innovation Explorative Data Scientist, LoB DATA € Analytics needs two things: building best models AND bringing them into production. Automation needed due to complexity / scale.
Copyright © SAS Institute Inc. All rights reserved. Summary & Next Steps Collect & explore data, learn patterns, and automate decisions. Data Science PLUS lines of businesses Only the integration in new processes will lead to business value. Everyone needs to understand the possibilities of ML. Machine Learning improves analytics Machine learning is an essential part of Advanced Analytics – and every corporate strategy. Operationalization requires discovery and action Automation and integration are more important than algorithms Machine Learning This e-book provides a primer on these innovative techniques as well as 10 best practices and a checklist for machine learning readiness.
Copyright © SAS Institute Inc. All rights reserved. Get in Contact with me! Dr. Andreas Becks, SAS https://twitter.com/becks_andreas https://www.linkedin.com/in/andreas-becks-10998058/

More Related Content

MACHINE LEARNING – THE WHY, WHAT AND HOW

  • 1. Copyright © SAS Institute Inc. All rights reserved. MACHINE LEARNING – THE WHY, WHAT, AND HOW Dr. Andreas Becks, SAS @becks_andreas
  • 2. Copyright © SAS Institute Inc. All rights reserved. Maschine Learning – An Example Everybody uses machine learning today – in your photo app it identifies faces and persons on your images.
  • 3. Copyright © SAS Institute Inc. All rights reserved. Cheap Compute Power and Parallel Processing “2.5 Exabytes of data are produced every day – that’s 90 years of HD videos.” “90 % of the worlds data today has been created in the last 2 years alone.” March 2015, DN Capital Availability of Data R&D on Algorithms Machine Learning – Why is ML so HOT? Three combining trends: big data, massive compute power, and better algorithms.
  • 4. Copyright © SAS Institute Inc. All rights reserved. Cognitive Computing Artificial Intelligence Machine Learning Neural Networks Deep Learning There is a lot of buzz around some related terms. Often confused, are they neither separted nor the same.
  • 5. Copyright © SAS Institute Inc. All rights reserved. Supervised Learning 10 Algorithms Machine Learning Engineers Need to Know Two major groups of algorithms form a set of machine learning tools. Source: KDnuggets based on Udacity’s Intro to Machine Learning Unsupervised Learning Naïve Bayes Classific. Linear Regression Logistic Regression Decision Tree Support Vector MachinesEnsemble Methods Unsupervised Learning Principal Component Analysis Cluster Algorithms Singular Value Decompo- sition Indepen- dent Component Analysis
  • 6. Copyright © SAS Institute Inc. All rights reserved. The Principle: Recognizing Activities Learning dependent patterns of movements Different sports, different movements –algorithms learns characteristic patterns in sensor data.
  • 7. Copyright © SAS Institute Inc. All rights reserved. Learning dependent patterns of movements X-Wrist X - Ankle Motion Trajectories Raw data by motion and inertial sensors X-Wrist True Activity Labels X - Ankle Training data: movement in context Machine Learning Support Vector Machines Neural Networks Learned classification The Principle: Recognizing Activities Combination of algorithms clusters the different raw data and connects it to different activties. Doing that, new and previously unknown incoming data can be appropriately classified.
  • 8. Copyright © SAS Institute Inc. All rights reserved. Use Cases for Machine Learning Manufacturing • Predictive Maintenance • Warranty reserve estimation • Propensity to buy • Demand forecasting • Telematics Healthcare • Alerts and diagnostics from real- time patient data • Risk stratification • Proactive health management Retail • Predictive inventory planning • Recommendation engines • Upsell and cross-channel marketing • Market segmentation • ROI and customer value Travel and Hospitality • Aircraft scheduling • Dynamic pricing • Consumer feedback (social media analysis) • Customer complaint resolution Energy • Smart grid management • Power usage analytics • Energy demand and supply optimization • Seismic data analysis • Carbon emission and trading Sources: Forbes Magazine, July 2016, Harvard Business Review, February 2016 Financial Services • Risk analytics and regulation • Customer segmentation • Cross-/Up-Sell • Campaign management • Credit worthiness evaluation More than a third of early movers also saw gains in bottom-line performance using machine-reengineering to slash 15% to 70% of costs from certain processes. Business processes in every industry will be affected.
  • 9. Copyright © SAS Institute Inc. All rights reserved. Example: Predict Maintenance of Computer Tomographs Thousands of devices, Tens of thousands event codes per day, sensor data 1,000s of predictive models Challenge: Predict failures of components 5 to 10 days in advance >70% precision and <20% false positives Impact on operative processes Real applications tend to become complex. It‘s not only 1 model / algorithm!
  • 10. Copyright © SAS Institute Inc. All rights reserved. Managing the Analytical Life Cycle Only integration of best models into business processes generates value Discover Deploy Prepare data Explore Model Integrate into business processes Execute Evaluate Ask IT, Business Analyst, LoB Robust Automation Actions Decisions Operations Experiments Data Science New data Innovation Explorative Data Scientist, LoB DATA € Analytics needs two things: building best models AND bringing them into production. Automation needed due to complexity / scale.
  • 11. Copyright © SAS Institute Inc. All rights reserved. Summary & Next Steps Collect & explore data, learn patterns, and automate decisions. Data Science PLUS lines of businesses Only the integration in new processes will lead to business value. Everyone needs to understand the possibilities of ML. Machine Learning improves analytics Machine learning is an essential part of Advanced Analytics – and every corporate strategy. Operationalization requires discovery and action Automation and integration are more important than algorithms Machine Learning This e-book provides a primer on these innovative techniques as well as 10 best practices and a checklist for machine learning readiness.
  • 12. Copyright © SAS Institute Inc. All rights reserved. Get in Contact with me! Dr. Andreas Becks, SAS https://twitter.com/becks_andreas https://www.linkedin.com/in/andreas-becks-10998058/

Editor's Notes

  1. https://www.sas.com/en_us/whitepapers/machine-learning-primer-108796.html