Zingography # 13 : Cognitive Behaviour + Data Science ; AB Test Validation Tool

I have been really fascinated by the capability of AB Testing Tool to make Designing Decisions using Data Science.
If you combine Machine Learning & Statistical Science to the same – then Previous Combo becomes more Potent & Effective.

AB Testing can be a tough Art to Master, even the most experienced ones go wrong all the time with their hypothesis & metrics selection.
Hence accepting your own & your colleagues varying opinions + navigating through the same to get most effective Long Term Impacts is they Key for Success.
But one should be honest to the science of AB Testing & how it is designed even if results are not favourable – it’s like a daily routine that should be practiced as it is.

What am here to discuss is the New Art of combining “Cognitive Design Behaviour with Data Science Algorithms” and especially use Spotify’s Playlist Recommendation for the same.

My Current Research Analysis says that Spotify’s Recommendation Engine is one of the best in this space!

Yeah better than Apple‘s iTunes, Alibaba‘s + Amazon’s Return HomePage Pages Recommendations or Similar SKU suggestions, Google‘s Search Engine or Google News Feed, Netflix‘s Similar Shows Features. What makes Spotify shine here is how it has used the Music Preferences Attributes along with Human Emotion Capture Calculations ! They use a unique score assigned to each song preferences & suggest them if your attributes matches the range of moods/preferences! Also their Engine is constantly improving & updating based on bigger cluster preferences. What I appreciate is that they are not using Other Platforms similar data but trusting self engines to contribute. Secondly, it empowers the customers to play with the algorithm to change preferences.

This slideshow requires JavaScript.

As per further search, AB Testing plays a very important role in making below decisions:

  • UI Decisions : Button Shape, Contrast colour, Position, Text, Headline, Icons (+ vs Heart), Widget Decisions, Hamburger Menu
  • Page Format – list view vs card view, the information architecture, number of information shared in a single page view
  • Metrics selection & Order Prioritisation for Making recommendations of Playlist
  • Deciding the Weightage of different Key Factors for engine’s Logic – which is the Highlight of Spotify’s Success!

  • Localising + Personalising the Site : https://www.thinkwithgoogle.com/intl/en-gb/success-stories/how-spotify-increased-premium-subscriptions-using-google-optimize-360/
  • Optimising the Keywords Search : When users in Germany searched for “audiobook” and clicked on one of Spotify’s ads, they were either brought to the custom page or to the original page.
  • Creating Culture of Experimentation & Real Time AB Testing Result platform which is most crucial. (They were earlier using Google’s Optimizely for a long time)

Did I ever share the perfect method of conducting an AB Test Experiment :

  1. Define the Problem – To increase conversion, to increase revenue
  2. Come up with a series of ideas to work around the same basis historical data, recent findings, industry insights – This should be a collective + collaborative process wherein everyone should be heard & allowed to explain their logic. Also while prospecting, one has to think about the impact % on success metrics with what confidence, duration, sample size.  Do not hesitate to use AB Testing calculator for same.
  3. Finally one has to prioritise these ideas basis their impact, time + effort + cost and decide on the order of these tests
  4. While designing the test – decide the Hypothesis that by doing so & so the impact shall increase. What is important to note is that while choosing these tests – they have to be such that can be proven only by data results. Also for tests with drastically different options – it can be a short duration test while for closer options, sample size hence duration has to be longer.
  5. So Hypothesis, success metric, options selection are very crucial aspects of the test
  6. Keep observing the performance of key metrics (Primary, Secondary at least) during the tests – no need to take sudden decisions basis this but observe the pattern.
  7. Let the test complete & observe the results – if results are drastically different, you have a clear winner. If test results are negative (do not worry), try with a different hypothesis & options. If test results are closer then decide whether to increase sample size or to discard the test or to go ahead with partial winner (last one not recommended but call can be taken depending on experience/circumstance/influence of other tests).
  8. Keep doing the same for different cases
Advertisements

Zingography 11 : Cognitive Abilities in PM

Cognitive Science involves linguistics, psychology, artificial intelligence, philosophy, neuroscience and anthropology. My learning & experience says that if we are able to include Cognitive Science into our Product Management Process – they results shall be much more refined, Long term & closest to objective.

Cognitive Science has to include multiple stakeholders views from :

  • Customers perspective
  • Team management perspective
  • Leadership & changing Business Landscape perspective

Am quite sure of developing successful models around the same for different PM Cycle stages & this is my effort for the same.

Below are the key PM Stages & recommended Models for the same :

  1. Business Strategy Roadmap based on Market Research & Secondary Research Data Insights — Model 1 (Leadership Management + Market Analysis – BCG Matrix, PLC, 7S Framework, Value Chain)
  2. Need Gap Analysis Identification — Model 2 (STP + 5Porters Forces)
  3. Recommendation Solutions & Prioritisation of Features (New & Enhancements) – Model 3 (Phase Gate Model/ Spider Mapping Technique ; High & Low Impact)
  4. User Persona Identification – Model 4 (Demography & Behaviour (Tech & Products) Mapping)
  5. Roadmapping + Project Management – Model 5 (Gantt Chart)
  6. BRD/ PRD – Model 6 (Process Note, Unified Modelling Language)
  7. MVP Approach – Model 7 (User – Action – Story ; Pain – Gain)
  8. User Journeys/Scenarios mapping – Model 8 (Decision Tree)
  9. Designing-> with quick dipsticks & quick changes around suggestions Model 9 : Neurological Emotional Branding + Decision of buying

Screenshot 2019-03-07 at 8.25.22 PM

10. Development/Middleware – Library & its adaptations for agile expansion
11. UAT all scenarios/Hackathon (Model 10) /CUG – AB Testing Hypothesis linked to Data          Mining & Big Data Analysis…. Statistics & its variance test analysis! Frequentist vs              Bayesian ..
12. Success Metrics formulation (Model 11) Data visualisation /K Nearest neighbours/              Regression/Clustering ; Random Forests; Time series/sequence; text mining!
13. Launch & Optimise
14. Team Management Model

Disclaimer : My suggestions are based on my experience, research, interactions with other companies & my own theories/understandings on this space. Am quite confident of their inter-relationship with each other.

Some Books I recommend in this regard are :

  • Design of everyday Life
  • Sapiens
  • Art of Deduction
  • Tao Te Ching by Lao Tzu
  • Cognitive Science
  • Psychology of Persuasion
  • Infographica

ZINGOGRAPHY : Tech/Product/UX/Startup Update # 10 – PM ToolKit

Please consider every PM to be a works-person, who needs tools apart from their skills to do a good job out of a situation!

Every worksmith/ carpenter/ chef, etc. is incomplete without their toolbox so its important as a Product Manager to be sure of your own sharpened tools basis your experience, intuition, comfort/compatibility, etc.

I also have now worked for 8+ years in different Products domain starting with Data, OTT, E-commerce, Retail Channels (B2B + B2C), Media, Food, Jewellery, FMCG, FinTech, Travel/OTA, AdTech, Transportation (Cabs/Trucks), etc.
And from my own & other PMs experience – let me share a list which I find is useful for one & all. These are compiled basis checking with other industries & PMs as well :

  1. Research Tools : SurveyMonkey, Google Forms, TypeForm
  2. Current Situation + Need Gap Analysis : Porter’s Frameworks – SWOT, 4P, STP, 5 Porter’s Force
  3. Project Management : Asana, Jira, Trello
  4. Team Management : Slack, Basecamp
  5. MVP & Road-mapping : Asana, Aha, ProdPad,
  6. Spec Writing : Word, DropBox Paper, GitHub
  7. User Scenarios Mapping : Excel, Smaply/StoriesonBoard
  8. Designing : Invision, Iconjar
  9. Coding/ Development : GitHub
  10. UX : Prototype,io, Axure
  11. Team screen sharing + feedback incorporation : Zeplin, Intercom
  12. AB Testing : VWO, Wasabi
  13. Analytics – Front End : Google Analytics, Firebase
  14. Analytics – Middle ware : Moengage, Clevertap, Appsflyer
  15. Analytics – Back End : SQL, ML Tools
  16. Campaign Management : Adobe 360
  17. Targeted Campaigns : Targetting
  18. Revenue + P&L Management : MS Excel Macro

Apart From this – the must have ingredient almost like Oiling is 5-6 hours of Reading, Networking, Experimenting, Failing, Sharing, etc.

All The Best : Let the Magic Begin!

10x10FT-wiece-Ksi-ki-P-ki-Biblioteki-Pok-j-Czaszka-Halloween-Klienta-Fotografia-T-o-Studio

ZINGOGRAPHY : Tech/Product/UX/Startup Update # 9

AB Testing is a Cultural & Personal Choice

Ittakes a lot number of weeks of research into white papers of statistics, informative articles on application, Live blogs for examples hunting, speaking to relevant stakeholders in competition & outside companies to discuss & link it with your current situation & problem statements to finally conform on your Approach.

I did the same with AB Testing!

And in all fairness, I have to admit that this has to be one of the most Surreal experiences since I realised there was a missing piece I was not including in the whole Picture/Frame/Painting of Product Design Thought Process.

AB Testing is critical to make your Product/Campaigns/Analytics/ Development Decision making simple & obvious decision making come out with an astounding clarity once AB Testing is conducted.
Plus how important it is to be persistent & have patience with the tests (design, conducting, results) — to know when to stop & when to start again.

There are two places where conducting AB Testing is a MUST :

  • Once when the prototypes of your App Key Pages are ready & you must know the initial response to them from your target consumer personas.
  • Second, before doing the campaigns & scaling the features/products — knowing the intricacies details in the form of headline, text, image, theme, colour palette, etc.

A few things must have technical :

  • AB Testing tool —

for beginners : VWO/Optimisely like SaaS tool ;

for mature organisations : Building the capability from scratch

for organisations in between who wish advanced readymade tool — I would recommend the hybrid way by using an open platform like Wasabi which can be customised to your requirements.

  • Good Quality Team with understanding of Statistics, SaaS Tools, Consumer Behavioural Analysis
  • Data Mart/Warehouse with access to Transactional Data as well as Online Behavioural Data with necessary cuts for segmentation basis Business Intelligence

A Few things in terms of Soft Power :

  • Open Mind — ready to question obvious right answers (infact more if they are obvious)
  • Capability to deep dive & look at intrinsic details
  • Collaborate with different teams/people to check if the findings or the direction of the findings are correct — this in my understanding is the most POTENT!

Organisations must insist their people to only come to leaders once they have collaborative evidences to move in a certain direction.

It may so happen that after spending significant time also — you may not come to an conclusive evidence & one should be open & amiable about the same & not push for an evidence for the sake of it.

I must thank quite a few people for the same but most of all Booking.com to highlight that there is something missing in my thought process — the webinar by Lukas was really helpful!

ZINGOGRAPHY : TECH/PRODUCT/UX/STARTUP UPDATE # 7.5

Sharing my list of most useful Apps (based on popularity, experience, usefulness) :

  • WhatsApp
  • Gmail
  • Twitter
  • Instagram
  • Amazon
  • Google Maps
  • Wikipedia
  • YouTube
  • Facebook
  • LinkedIn

Last two are my least favourite of all – they are just latching around for lack of options!

Will add more in due course.

 

This slideshow requires JavaScript.

There shall be changes in coming years but one has to adapt the learnings from the top performing apps.

Create a free website or blog at WordPress.com.

Up ↑