Insights into Customer Behavior from Clickstream Data by Ronald Nowling
•
4 likes•2,075 views
This document discusses insights that can be gained from analyzing clickstream data collected from a company's customer knowledgebase and portal. It describes how clickstream data containing 61 million page views and 500,000 pages from 125,000 registered users can be processed and analyzed to build customer profiles, improve search and recommendations, and guide the selection of new knowledgebase topics. Potential applications include using customer profiles to aid sales teams, creating a recommendation system for the knowledgebase, and enhancing the customer portal search.
Recommended
More Related Content
What's hot
What's hot (20)
Viewers also liked
Viewers also liked (20)
Similar to Insights into Customer Behavior from Clickstream Data by Ronald Nowling
Similar to Insights into Customer Behavior from Clickstream Data by Ronald Nowling (20)
More from Spark Summit
More from Spark Summit (20)
Recently uploaded
Recently uploaded (20)
Insights into Customer Behavior from Clickstream Data by Ronald Nowling
- 1. Insights into Customer Behavior from Clickstream Data Ronald J. Nowling Red Hat, Inc. rnowling@redhat.com http://rnowling.github.io/
- 2. Who Am I? • Software Engineer at Red Hat • Data Science Team, Emerging Technologies – Evaluate solutions in open-source Big Data space – Ensure software works for Red Hat customers – Promote data science internally through consulting projects • Apache Bigtop PMC 2
- 4. Clickstream Data 61 million page views 4
- 5. Clickstream Data 61 million page views 125,000 registered users 5
- 6. Clickstream Data 61 million page views 125,000 registered users 500,000 pages 6
- 7. Clickstream Data 61 million page views 125,000 registered users 500,000 pages 125,000 knowledgebase articles 7
- 8. Potential Applications • Build customer profiles to aid sales teams • Recommendation system for knowledgebase • Improve customer portal search • Guide selection of new knowledgebase topics by content writers 8
- 9. 9 Strip Formatting Clean Words Vectorize Cluster What are the different types of kernel packages in Red Hat Enterprise Linux? ============================================================= Issue ------ What are the different types of kernel packages in Red Hat Enterprise Linux? Environment --------------- Red Hat Enterprise Linux Resolution ------------ Red Hat Enterprise Linux contains the following kernel packages:
- 10. 10 Strip Formatting Clean Words Vectorize Cluster What are the different types of kernel packages in Red Hat Enterprise Linux Issue What are the different types of kernel packages in Red Hat Enterprise Linux Environment Red Hat Enterprise Linux Resolution Red Hat Enterprise Linux contains the following kernel packages some may not apply to your architecture and not all are available in all major releases kernel contains the kernel and following key features
- 11. 11 Strip Formatting Clean Words Vectorize Cluster What are the different types of kernel packages in Red Hat Enterprise Linux Issue What are the different types of kernel packages in Red Hat Enterprise Linux Environment Red Hat Enterprise Linux Resolution Red Hat Enterprise Linux contains the following kernel packages some may not apply to your architecture and not all are available in all major releases kernel contains the kernel and following key features
- 12. 12 Strip Formatting Clean Words Vectorize Cluster What are the different type of kernel package in Red Hat Enterprise Linux Issue What are the different type of kernel package in Red Hat Enterprise Linux Environment Red Hat Enterprise Linux Resolution Red Hat Enterprise Linux contain the follow kernel package some may not apply to your architecture and not all are available in all major release kernel contain the kernel and follow key feature
- 13. 13 Strip Formatting Clean Words Vectorize Cluster What are the different type of kernel package in Red Hat Enterprise Linux Issue What are the different type of kernel package in Red Hat Enterprise Linux Environment Red Hat Enterprise Linux Resolution Red Hat Enterprise Linux contain the follow kernel package some may not apply to your architecture and not all are available in all major release kernel contain the kernel and follow key feature
- 14. 14 Strip Formatting Clean Words Vectorize Cluster different type kernel package Red Hat Enterprise Linux Issue different type kernel package Red Hat Enterprise Linux Environment Red Hat Enterprise Linux Resolution Red Hat Enterprise Linux contain kernel package apply architecture available major release kernel contain kernel follow key feature
- 15. 15 Strip Formatting Clean Words Vectorize Cluster kernel: 5 red: 4 hat: 4 enterprise: 4 linux: 4 package: 3 contain: 3 different: 2 type: 2 intel: 2 environment: 1 resolution: 1 follow: 1 system: 1
- 16. 16 Strip Formatting Clean Words Vectorize Cluster kernel: 5 red: 4 hat: 4 enterprise: 4 linux: 4 package: 3 contain: 3 different: 2 type: 2 intel: 2 environment: 1 resolution: 1 follow: 1 system: 1
- 17. 17 Strip Formatting Clean Words Vectorize Cluster kernel: 5 red: 4 hat: 4 enterprise: 4 linux: 4 package: 3 contain: 3
- 20. Topics openshift gear cartridge online node broker vm rhev virtualization disk glusterfs storage volume brick rhs glusterd node client mount geo rhel support driver hp hardware version firmware card intel 20
- 21. Topics openshift gear cartridge online node broker vm rhev virtualization disk glusterfs storage volume brick rhs glusterd node client mount geo rhel support driver hp hardware version firmware card intel 21
- 22. Topics openshift gear cartridge online node broker vm rhev virtualization disk glusterfs storage volume brick rhs glusterd node client mount geo rhel support driver hp hardware version firmware card intel 22
- 23. Topics openshift gear cartridge online node broker vm rhev virtualization disk glusterfs storage volume brick rhs glusterd node client mount geo rhel support driver hp hardware version firmware card intel 23
- 24. Topics openshift gear cartridge online node broker vm rhev virtualization disk glusterfs storage volume brick rhs glusterd node client mount geo rhel support driver hp hardware version firmware card intel 24
- 26. Clickstream Processing Parse Raw Daily Page Views Clean & Filter Raw Daily Page Views Raw Daily Page Views Parse Parse Clean & Filter Clean & Filter Accounts Aggregate Topic View Counts Project onto Topics 26
- 27. Clickstream Processing Parse Raw Daily Page Views Clean & Filter Raw Daily Page Views Raw Daily Page Views Parse Parse Clean & Filter Clean & Filter Accounts Aggregate Topic View Counts Project onto Topics 27
- 28. Clickstream Processing Parse Raw Daily Page Views Clean & Filter Raw Daily Page Views Raw Daily Page Views Parse Parse Clean & Filter Clean & Filter Accounts Aggregate Topic View Counts Project onto Topics 28
- 29. Clickstream Processing Parse Raw Daily Page Views Clean & Filter Raw Daily Page Views Raw Daily Page Views Parse Parse Clean & Filter Clean & Filter Accounts Aggregate Topic View Counts Project onto Topics 29
- 30. Clickstream Processing Parse Raw Daily Page Views Clean & Filter Raw Daily Page Views Raw Daily Page Views Parse Parse Clean & Filter Clean & Filter Accounts Aggregate Topic View Counts Project onto Topics 30
- 31. Customer Profiles • Dominant topics – JBoss – Red Hat Enterprise Virtualization – Hardware support – Gluster – Booting into rescue mode – Packages 31
- 32. Customer Profiles • Supporting topics – Logging – LDAP – Samba – High resource usage – File systems / LVM / block devices – Networking 32
- 33. Customer Profiles • JBoss and RHEV appear in combination with a number of other products • Some products only appear by themselves with supporting topics (logging, networking, filesystems) – OpenShift – Gluster 33
- 35. Malformed TSV Files • Gzip files need to be read sequentially • Tab-separated, no quoting (in theory!) • Escaped tabs and newlines within records • E.g., n or t • Improperly escaped tabs and newlines • E.g., t vs t • Extraneous unmatched quote marks • E.g., ‘some_user 35
- 36. Lessons Learned • Consider custom Hadoop input formats for tricky file formats • Verify everything – what works in general may not work for you – Stemming – Filtering most frequent words – K-Means vs LDA 36
- 37. Lessons Learned • K-Means – Improve accuracy: Multiple runs, more iterations • Watch out for memory leaks – Un-persist cached RDDs – Un-persist broadcasted variables • Parquet for performance 37
- 38. Potential Applications • Build customer profiles to aid sales teams • Recommendation system for knowledgebase • Improve customer portal search • Guide selection of new knowledgebase topics for content writers 38
- 40. QUESTIONS 40