Turning Analysis into Action with APIs - Superweek2017
•Download as PPTX, PDF•
5 likes•1,538 views
Presentation given by Peter Meyer and Mark Edmondson and Superweek 2017 in Hungary. Includes three examples of using APIs in a tag management solution to give better data to make decisions and use predictions. 1.
Report
Share
Turning Analysis into Action with APIs - Superweek2017
- 1. TURNING ANALYSIS INTO ACTION WITH APIs
- 2. • Digital business focus • 15+ years of experience • Web Analytics House 2013, 2014, 2015, 2016, 2017 • Value-driven business • More than 40 people in Denmark, Sweden & Norway About IIH Nordic
- 3. About Us Mark Edmondson • In digital since 2006 • Data Insight Developer • Google Developer Expert for Google Analytics • RStudio Advocate • cloudyR contributor • @HoloMarkeD Peter Meyer • In digital since 1997 • Analytics Technician • TMS and Analytics implementer • @pmeyerdk
- 4. Agenda • What are actionable analysis APIs? • Example 1 - Weather API - IBM • Example 2 - Custom prediction API - Prefetching • Example 3 - Text sentiment API – Google/Algorithmia Machine Learning • Future opportunities
- 7. Collect Data Analyse Data Change something Reporting APIs Tracking APIs Analysis APIs An Analytics Workflow
- 8. Collect Data Analyse Data Change something Reporting APIs Tracking APIs Analysis APIs An Analytics Workflow
- 10. Analysis API An API that transforms data into useful information
- 11. Examples of actionable analysis APIs • Visualisations for decision support (dashboards) • Multivariant testing • Bid managers • Enrichment of data - weather • Content prediction - prefetching • Text analysis – machine learning API We will talk today about these ones: …but others include:
- 13. Deployment • Only one webservice used • Geo- and weather data in one go • A bunch of information returned
- 14. Deployment
- 15. Analysis • Take daily lag to negate spurious trend correlation • tscount() R package for poisson distribution • 16% ±4% extra visitors on rainy days
- 20. https://www.noisetosignal.io/2016/11/using-google-analytics-to-predict-clicks-and-speed-up-your-website/ Simpler method using offline analysis and deploying through a GTM lookup table
- 22. Real-time sentiment tracking of customer service forums/comment sections Categorise topics your customers care about
- 24. Deployment - Algorithmia • Stanford NLP Sentiment Analysis • https://algorithmia.com/
- 25. Deployment - Algorithmia I really love ice cream very much!
- 26. Deployment - Google • Google Cloud Natural Language API (beta) • https://cloud.google.com/natural-language/
- 27. Deployment - Google I really love ice cream very much! http://glaforge.appspot.com/article/sentiment-analysis-on-tweets
- 28. Recent example at gov.uk https://gdsdata.blog.gov.uk/2016/12/20/using-machine-learning-to-classify-user-comments-on-gov-uk/
- 31. Preparation for the singularity • Get your data tidy and out of silos • Start prototyping models • Skill up in a ML tech stack
- 32. Skill up in a machine learning tech stack • Google BigQuery • Google Compute Engine • Tensorflow • Dataproc (Spark) • Redshift/Athena • Amazon EMR • EC2 • S3 • Amazon Machine Learning • SQL Data Warehouse • Azure • Microsoft R • Microsoft Cognitive Programming languages: R, Python, bash, JavaScript, Scala, Java, Julia(?), SQL
- 33. ML: Google Flavoured Build your own self- driving car! ....or for simpler use cases use the pre- trained models available using easy to use APIs
- 34. A Microsoft Cognitive API Example https://matt-stannard.blogspot.dk/2016/12/measuring-footfall-with-google.html
- 35. • Look to reduce time to actions via APIs • GTM can do more than tracking • Skill up in a machine learning tech stack Summary
- 36. Thank you! Mark Edmondson mark@iihnordic.com @HoloMarkeD https://www.linkedin.com/in/markpeteredmondson Peter Meyer peter.meyer@iihnordic.com @pmeyerdk https://www.linkedin.com/in/pmeyerdk
Editor's Notes
- Hos IIH tror vi på at virksomheder har en massivt uudnyttet potentiale når det kommer til det digitale. Vi har gennem vores arbejde lært at digital forretning bygger på data, men at virksomheder nogle gange har brug for hjælp til at lære at forstå og udnytte alle deres muligheder. Det der adskiller os er, at vi har taget digital effektmåling og på den baggrund har skabt nogle virkelige effektive ydelser, der hjælper både virksomheder, markedsføringsfolk og salgsfolk med at tænke digitalt både internt og ekstern baseret på hvordan man rent faktisk skaber resultater online og komme godt i gang med en digital tranformation. ”Måske: Man kan sige de fleste virksomheder står stadigvæk kun med tæerne i vandkanten i forhold det hav af digitale muligheder der findes. I den forbindelse ser vi det som vores opgave at lære dem at svømme.” @tænker forrretningsorienteret: Vi er ikke et traditionelt online bureau og vores kunder ser os typiske mere som et resultatbureau, der får tingene til at ske forretningsmæssigt
- Enrich – Learn - React
- Mark to talk about R stuff in this slide? How do Peter explain best?
- User comments/reviews Content