Good bye conversion rate - a smarter way to optimising Search Engine Result Pages
0 likes274 views
The document discusses new methodologies for optimizing search engine result pages (SERPs) through usability-based split testing, which focuses on improving user interaction rather than sales metrics. It outlines a system called Wappu that employs a machine learning model to evaluate usability and gather recommendations for optimization. The study demonstrates significant improvements in SERP usability and suggests future work in creating catalogs for various web page categories and enhancing data quality.
![Usability-based Split Testing
12
Interface A Interface B
Questionnaire
[WaPPU – Usability based A/B-Testing
Speicher, Both, Gaedke, ICWE2014]
Martin Gaedke - http://vsr.informatik.tu-chemnitz.de
WaPPU
Usability System
(Naive Bayes classier for the
learning)
Model
for
Usability](https://image.slidesharecdn.com/is-swis2017-3-170328065340/85/Good-bye-conversion-rate-a-smarter-way-to-optimising-Search-Engine-Result-Pages-12-320.jpg)
![Usability-based Split Testing
13
Interface A Interface B
[WaPPU – Usability based A/B-Testing
Speicher, Both, Gaedke, ICWE2014]
Martin Gaedke - http://vsr.informatik.tu-chemnitz.de
WaPPU
Usability System
TRAINED
Model
for
Usability](https://image.slidesharecdn.com/is-swis2017-3-170328065340/85/Good-bye-conversion-rate-a-smarter-way-to-optimising-Search-Engine-Result-Pages-13-320.jpg)
![19
SERP Optimization Suite
(S.O.S.)
WaPPU
for evaluation
Catalog
of best practices
Martin Gaedke - http://vsr.informatik.tu-chemnitz.de
[S.O.S.: Does Your Search Engine Results Page (SERP) Need Help?
Speicher, Both, Gaedke, CHI 2015]](https://image.slidesharecdn.com/is-swis2017-3-170328065340/85/Good-bye-conversion-rate-a-smarter-way-to-optimising-Search-Engine-Result-Pages-18-320.jpg)
Good bye conversion rate - a smarter way to optimising Search Engine Result Pages
- 1. Faculty of Computer Science Professorship Distributed and self-organizing Systems Good bye conversion rate a smarter way to optimising Search Engine Results Pages MartinGaedke.com VSR.Informatik.TU-Chemnitz.de ///// IS-SWIS 2017, Rotterdam, February 9, 2017///
- 3. Search Engine Result Pages (SERPs) 3Martin Gaedke - http://vsr.informatik.tu-chemnitz.de
- 4. (simplified) Motivation 4 Evaluation Method Efficient? Effective? User Testing ✖ ✔ Usability Inspection ✖ ✔ Split Testing ✔ ✖ Martin Gaedke - http://vsr.informatik.tu-chemnitz.de
- 5. Split Testing 5 Buy this Buy this Martin Gaedke - http://vsr.informatik.tu-chemnitz.de Version A Version B
- 6. Conversion Rate: proportion of visitors to a website who take action due to subtle requests from marketers, SEOs, (semantic) data providers etc. The problem with Split Testing 6Martin Gaedke - http://vsr.informatik.tu-chemnitz.de (source: Wikipedia.com)
- 7. Version A: Getting the User‘s Zip Code 7Martin Gaedke - http://vsr.informatik.tu-chemnitz.de
- 8. 8 $$$ ≠ Usability Jakob Nielsen: Putting A/B Testing in Its Place, http://www.nngroup.com/articles/putting-ab-testing-in-its-place/ Martin Gaedke - http://vsr.informatik.tu-chemnitz.de
- 9. Goal: to leverage the advantages of split testing AND to facilitate effective usability evaluation
- 10. Idea: Rethink the target measure from the users point of view (i.e. development & user – not sales) : Usability as a measure for split testing
- 11. 11 Idea: Infer quantitative measure of usability from user interactions. Martin Gaedke - http://vsr.informatik.tu-chemnitz.de
- 12. Usability-based Split Testing 12 Interface A Interface B Questionnaire [WaPPU – Usability based A/B-Testing Speicher, Both, Gaedke, ICWE2014] Martin Gaedke - http://vsr.informatik.tu-chemnitz.de WaPPU Usability System (Naive Bayes classier for the learning) Model for Usability
- 13. Usability-based Split Testing 13 Interface A Interface B [WaPPU – Usability based A/B-Testing Speicher, Both, Gaedke, ICWE2014] Martin Gaedke - http://vsr.informatik.tu-chemnitz.de WaPPU Usability System TRAINED Model for Usability
- 14. Usability Model allows for: f(cause) = score (cause is part of usability) 14Martin Gaedke - http://vsr.informatik.tu-chemnitz.de
- 15. Sure! f(cause) = score this function is not bijective (Not possible to infer optimizations from usability scores ) Limitations? 16Martin Gaedke - http://vsr.informatik.tu-chemnitz.de
- 16. How to overcome the f(cause) = score limitations? 17
- 17. Catalog of best practices a.k.a. Set of causes and optimizations 18
- 18. 19 SERP Optimization Suite (S.O.S.) WaPPU for evaluation Catalog of best practices Martin Gaedke - http://vsr.informatik.tu-chemnitz.de [S.O.S.: Does Your Search Engine Results Page (SERP) Need Help? Speicher, Both, Gaedke, CHI 2015]
- 19. 20 fu (score) = {C, C'} u = usability item number C = potential causes C' = countermeasures Martin Gaedke - http://vsr.informatik.tu-chemnitz.de
- 20. S.O.S. example: "We have a problem with Distraction" 21Martin Gaedke - http://vsr.informatik.tu-chemnitz.de
- 23. 27 User Study • 81 participants (~62% male) • avg. age = 31.08 years • Task: Solve a problem
- 24. 28 “Find a birthday present for a good friend that does not cost more than 50 Euros.” Martin Gaedke - http://vsr.informatik.tu-chemnitz.de
- 27. 32 Results old SERP new SERP informativeness -0.17 â < -0.02 â understandability 0.34 â < 0.45 â confusion 0.30 â < 0.38 â distraction* 0.36 â < 0.62 ä readability 0.45 â < 0.52 â information density* 0.04 â < 0.43 ä accessibility 0.06 â < 0.07 â overall usability* 59.86% â < 67.50% ä Martin Gaedke - http://vsr.informatik.tu-chemnitz.de
- 29. n S.O.S. significantly improved SERP usability n Approach developed using HCD/DT n obtaining usability scores through WaPPU and n recommendations for optimization from a catalog for suboptimal scores n http://vsr.informatik.tu-chemnitz.de/demo/SOS Conclusions 34Martin Gaedke - http://vsr.informatik.tu-chemnitz.de
- 30. n Catalogs for other categories of Web pages n Creating trained model for web page and site categories n Crating more generic and reusable catalogs n Reducing the learning time n Applying the approach to the quality of linked enterprise data n Improving: incorrect, incomplete etc. data n Dealing with: Co-evolution, Coherence etc. n Data Quality à Fit for business use n LEDS project: http://www.leds-projekt.de/ Future Work 35Martin Gaedke - http://vsr.informatik.tu-chemnitz.de
- 31. 36Martin Gaedke - http://vsr.informatik.tu-chemnitz.de Data Quality can be interpreted as the degree to which data fits to current requirements 𝐷𝑄#$%&'(& = ∑ ∑ 𝜔-'. / 𝑓𝑢𝑙𝑓𝑖𝑙𝑙 𝑟𝑒𝑞, 𝑜𝑏𝑗-'.<='>'?< + 𝜑
- 33. Chemnitz University of Technology #VSR Thank You! martin@gaedke.com VSR.Informatik.TU-Chemnitz.de @gaedke /gaedke 38Martin Gaedke - http://vsr.informatik.tu-chemnitz.de