SlideShare a Scribd company logo
1 of 19
+
Recommendation Assumptions
Prototyping Day @ Mozilla London
3 September 2015
Engineering Summit @ BBC
7 March 2018
Presented at
+
Recommendations
types
Personal vs. Non personal
+
Recommendations types
 Personalized
 User-interaction driven (passive/active)
 Non personalized
 Editorially curated
 Stats Based
+
User-interaction driven
passive interaction
active interaction
A set of user interactions with the
system entails a set of (possibly
empty) preferences - inference
Can be used to reinforce
recommendations (like, thumbup,
follow, dislike, etc.)
+
Recommendations types
 Personalized
 User-interaction driven (passive/active)
 Non personalized
 Editorially curated
 Stats Based
+
Editorially curated
content
The BBC
+
User rating
Google
+
Most popular
If more than N% + K of people liked,
listened to, blablablabed about
something (+/- standard deviation), this
something is likely to be
recommended.
+
Content similarity
It can be content-to-content or cross content. To calculate the similarity we
can use the actual content or the metadata or both.
+
Co-occurrence
relationship (market
basket analysis)
Understand what products or services
are commonly purchased together.
If you consume a certain group
(cluster) of contents, you are more (or
less) likely to consume another group
of items – Beers and nappies
+
Assumptions
 Similarity and Correlation
 User activity assumptions
 Device sensor analytics (accelerometer, gyroscope, compass,
barometer, ambient light sensor, proximity sensor,
thermometer, camera, microphone, GPS, etc.)
+
Perturbations (external influences)
 Model building phase
 Recommendation phase
+
Mood
+
Wear & Tear
+
Does the time matter?
+
Does the time matter?
 Are preferences or statistics about a topic valid forever?
 If not, what’s the “best” time window to take in account?
 How can we model a preference modification during the time?
(Aging, change of taste)
 How a good/bad feedback can affect a recommendation in the
future and for how long?
+
Empathy (induced preferences)
+
I’ve got questions for you
 Inheritance, taxonomy, membership, how do we use these
relationships between contents in a domain in order to infer a
user interest?
 Is the interest of a user black and white only? How can I
express different type of interests (if any)?
 Can we improve the quality of the user experience by
presenting the right “amount” of information of a recommended
content according to
 type and level of interest?
 time available to consume the content?
 mood?
+
Thank you
Simone.Spaccarotella@bbc.co.uk
Senior Software Engineer | BBC Sounds

More Related Content

Similar to Recommendations assumptions

Basic social media monitoring tools
Basic social media monitoring toolsBasic social media monitoring tools
Basic social media monitoring tools
Adam Vincenzini
 
Web metrics-cell-carrier-buzz-on-the-web-12063
Web metrics-cell-carrier-buzz-on-the-web-12063Web metrics-cell-carrier-buzz-on-the-web-12063
Web metrics-cell-carrier-buzz-on-the-web-12063
Lextant
 

Similar to Recommendations assumptions (20)

Analytics for Virtual Worlds
Analytics for Virtual WorldsAnalytics for Virtual Worlds
Analytics for Virtual Worlds
 
Getting Under the Hood: What Analytics and Metrics Can Show You About Your We...
Getting Under the Hood: What Analytics and Metrics Can Show You About Your We...Getting Under the Hood: What Analytics and Metrics Can Show You About Your We...
Getting Under the Hood: What Analytics and Metrics Can Show You About Your We...
 
The subtle art of recommendation
The subtle art of recommendationThe subtle art of recommendation
The subtle art of recommendation
 
20120140506003
2012014050600320120140506003
20120140506003
 
Service Tools and Social Media Data Sharing Use Case
Service Tools and Social Media Data Sharing Use CaseService Tools and Social Media Data Sharing Use Case
Service Tools and Social Media Data Sharing Use Case
 
Everything You Always Wanted to Know About Bad UX Research But Were Afraid to...
Everything You Always Wanted to Know About Bad UX Research But Were Afraid to...Everything You Always Wanted to Know About Bad UX Research But Were Afraid to...
Everything You Always Wanted to Know About Bad UX Research But Were Afraid to...
 
Find the Metrics That Matter for Your Newsroom
Find the Metrics That Matter for Your NewsroomFind the Metrics That Matter for Your Newsroom
Find the Metrics That Matter for Your Newsroom
 
Social Media Madness - join or die
Social Media Madness - join or dieSocial Media Madness - join or die
Social Media Madness - join or die
 
How we Snack on Information (how not to get forgotten/ lost in a self-service...
How we Snack on Information (how not to get forgotten/ lost in a self-service...How we Snack on Information (how not to get forgotten/ lost in a self-service...
How we Snack on Information (how not to get forgotten/ lost in a self-service...
 
Basic social media monitoring tools
Basic social media monitoring toolsBasic social media monitoring tools
Basic social media monitoring tools
 
Practical Social Analytics
Practical Social AnalyticsPractical Social Analytics
Practical Social Analytics
 
Maura Tuohy
Maura TuohyMaura Tuohy
Maura Tuohy
 
Behavioral responsivness
Behavioral responsivnessBehavioral responsivness
Behavioral responsivness
 
Using Research to Grow Your Business
Using Research to Grow Your BusinessUsing Research to Grow Your Business
Using Research to Grow Your Business
 
What to Look for in a Social Media Analytics Tool
What to Look for in a Social Media Analytics ToolWhat to Look for in a Social Media Analytics Tool
What to Look for in a Social Media Analytics Tool
 
iMedia October Breakthrough Summit: Insight Address: "Search and Discovery o...
iMedia October Breakthrough Summit:  Insight Address: "Search and Discovery o...iMedia October Breakthrough Summit:  Insight Address: "Search and Discovery o...
iMedia October Breakthrough Summit: Insight Address: "Search and Discovery o...
 
Alex wright mons_workshop_051214
Alex wright mons_workshop_051214Alex wright mons_workshop_051214
Alex wright mons_workshop_051214
 
Web metrics-cell-carrier-buzz-on-the-web-12063
Web metrics-cell-carrier-buzz-on-the-web-12063Web metrics-cell-carrier-buzz-on-the-web-12063
Web metrics-cell-carrier-buzz-on-the-web-12063
 
Web Metrics - Cell Carrier Buzz on the Web
Web Metrics - Cell Carrier Buzz on the WebWeb Metrics - Cell Carrier Buzz on the Web
Web Metrics - Cell Carrier Buzz on the Web
 
A NOVEL RESEARCH PAPER RECOMMENDATION SYSTEM
A NOVEL RESEARCH PAPER RECOMMENDATION SYSTEMA NOVEL RESEARCH PAPER RECOMMENDATION SYSTEM
A NOVEL RESEARCH PAPER RECOMMENDATION SYSTEM
 

More from Simone Spaccarotella

A System for Stratified Datalog Programs - Master's thesis presentation
A System for Stratified Datalog Programs - Master's thesis presentationA System for Stratified Datalog Programs - Master's thesis presentation
A System for Stratified Datalog Programs - Master's thesis presentation
Simone Spaccarotella
 

More from Simone Spaccarotella (7)

BBC Sounds Update 28 November 2019
BBC Sounds Update 28 November 2019BBC Sounds Update 28 November 2019
BBC Sounds Update 28 November 2019
 
BBC Sounds Update - Play team (Snowy Edition)
BBC Sounds Update - Play team (Snowy Edition)BBC Sounds Update - Play team (Snowy Edition)
BBC Sounds Update - Play team (Snowy Edition)
 
BBC Sounds Web Next Architecture
BBC Sounds Web Next ArchitectureBBC Sounds Web Next Architecture
BBC Sounds Web Next Architecture
 
HTTP/2 and web development practices
HTTP/2 and web development practicesHTTP/2 and web development practices
HTTP/2 and web development practices
 
AWS account migration for BBC iPlayer Radio
AWS account migration for BBC iPlayer RadioAWS account migration for BBC iPlayer Radio
AWS account migration for BBC iPlayer Radio
 
A System for Stratified Datalog Programs - Master's thesis presentation
A System for Stratified Datalog Programs - Master's thesis presentationA System for Stratified Datalog Programs - Master's thesis presentation
A System for Stratified Datalog Programs - Master's thesis presentation
 
MicroWSMO editor - Bachelor's thesis presentation
MicroWSMO editor - Bachelor's thesis presentationMicroWSMO editor - Bachelor's thesis presentation
MicroWSMO editor - Bachelor's thesis presentation
 

Recently uploaded

Team Transformation Tactics for Holistic Testing and Quality (NewCrafts Paris...
Team Transformation Tactics for Holistic Testing and Quality (NewCrafts Paris...Team Transformation Tactics for Holistic Testing and Quality (NewCrafts Paris...
Team Transformation Tactics for Holistic Testing and Quality (NewCrafts Paris...
Lisi Hocke
 
Jax, FL Admin Community Group 05.14.2024 Combined Deck
Jax, FL Admin Community Group 05.14.2024 Combined DeckJax, FL Admin Community Group 05.14.2024 Combined Deck
Jax, FL Admin Community Group 05.14.2024 Combined Deck
Marc Lester
 

Recently uploaded (20)

architecting-ai-in-the-enterprise-apis-and-applications.pdf
architecting-ai-in-the-enterprise-apis-and-applications.pdfarchitecting-ai-in-the-enterprise-apis-and-applications.pdf
architecting-ai-in-the-enterprise-apis-and-applications.pdf
 
Abortion Clinic In Pretoria ](+27832195400*)[ 🏥 Safe Abortion Pills in Pretor...
Abortion Clinic In Pretoria ](+27832195400*)[ 🏥 Safe Abortion Pills in Pretor...Abortion Clinic In Pretoria ](+27832195400*)[ 🏥 Safe Abortion Pills in Pretor...
Abortion Clinic In Pretoria ](+27832195400*)[ 🏥 Safe Abortion Pills in Pretor...
 
Team Transformation Tactics for Holistic Testing and Quality (NewCrafts Paris...
Team Transformation Tactics for Holistic Testing and Quality (NewCrafts Paris...Team Transformation Tactics for Holistic Testing and Quality (NewCrafts Paris...
Team Transformation Tactics for Holistic Testing and Quality (NewCrafts Paris...
 
Spring into AI presented by Dan Vega 5/14
Spring into AI presented by Dan Vega 5/14Spring into AI presented by Dan Vega 5/14
Spring into AI presented by Dan Vega 5/14
 
Tree in the Forest - Managing Details in BDD Scenarios (live2test 2024)
Tree in the Forest - Managing Details in BDD Scenarios (live2test 2024)Tree in the Forest - Managing Details in BDD Scenarios (live2test 2024)
Tree in the Forest - Managing Details in BDD Scenarios (live2test 2024)
 
What is a Recruitment Management Software?
What is a Recruitment Management Software?What is a Recruitment Management Software?
What is a Recruitment Management Software?
 
Salesforce Introduced Zero Copy Partner Network to Simplify the Process of In...
Salesforce Introduced Zero Copy Partner Network to Simplify the Process of In...Salesforce Introduced Zero Copy Partner Network to Simplify the Process of In...
Salesforce Introduced Zero Copy Partner Network to Simplify the Process of In...
 
The Evolution of Web App Testing_ An Ultimate Guide to Future Trends.pdf
The Evolution of Web App Testing_ An Ultimate Guide to Future Trends.pdfThe Evolution of Web App Testing_ An Ultimate Guide to Future Trends.pdf
The Evolution of Web App Testing_ An Ultimate Guide to Future Trends.pdf
 
[GeeCON2024] How I learned to stop worrying and love the dark silicon apocalypse
[GeeCON2024] How I learned to stop worrying and love the dark silicon apocalypse[GeeCON2024] How I learned to stop worrying and love the dark silicon apocalypse
[GeeCON2024] How I learned to stop worrying and love the dark silicon apocalypse
 
Alluxio Monthly Webinar | Simplify Data Access for AI in Multi-Cloud
Alluxio Monthly Webinar | Simplify Data Access for AI in Multi-CloudAlluxio Monthly Webinar | Simplify Data Access for AI in Multi-Cloud
Alluxio Monthly Webinar | Simplify Data Access for AI in Multi-Cloud
 
Prompt Engineering - an Art, a Science, or your next Job Title?
Prompt Engineering - an Art, a Science, or your next Job Title?Prompt Engineering - an Art, a Science, or your next Job Title?
Prompt Engineering - an Art, a Science, or your next Job Title?
 
^Clinic ^%[+27788225528*Abortion Pills For Sale In birch acres
^Clinic ^%[+27788225528*Abortion Pills For Sale In birch acres^Clinic ^%[+27788225528*Abortion Pills For Sale In birch acres
^Clinic ^%[+27788225528*Abortion Pills For Sale In birch acres
 
OpenChain @ LF Japan Executive Briefing - May 2024
OpenChain @ LF Japan Executive Briefing - May 2024OpenChain @ LF Japan Executive Briefing - May 2024
OpenChain @ LF Japan Executive Briefing - May 2024
 
From Theory to Practice: Utilizing SpiraPlan's REST API
From Theory to Practice: Utilizing SpiraPlan's REST APIFrom Theory to Practice: Utilizing SpiraPlan's REST API
From Theory to Practice: Utilizing SpiraPlan's REST API
 
Evolving Data Governance for the Real-time Streaming and AI Era
Evolving Data Governance for the Real-time Streaming and AI EraEvolving Data Governance for the Real-time Streaming and AI Era
Evolving Data Governance for the Real-time Streaming and AI Era
 
Jax, FL Admin Community Group 05.14.2024 Combined Deck
Jax, FL Admin Community Group 05.14.2024 Combined DeckJax, FL Admin Community Group 05.14.2024 Combined Deck
Jax, FL Admin Community Group 05.14.2024 Combined Deck
 
Secure Software Ecosystem Teqnation 2024
Secure Software Ecosystem Teqnation 2024Secure Software Ecosystem Teqnation 2024
Secure Software Ecosystem Teqnation 2024
 
Weeding your micro service landscape.pdf
Weeding your micro service landscape.pdfWeeding your micro service landscape.pdf
Weeding your micro service landscape.pdf
 
^Clinic ^%[+27788225528*Abortion Pills For Sale In witbank
^Clinic ^%[+27788225528*Abortion Pills For Sale In witbank^Clinic ^%[+27788225528*Abortion Pills For Sale In witbank
^Clinic ^%[+27788225528*Abortion Pills For Sale In witbank
 
Entropy, Software Quality, and Innovation (presented at Princeton Plasma Phys...
Entropy, Software Quality, and Innovation (presented at Princeton Plasma Phys...Entropy, Software Quality, and Innovation (presented at Princeton Plasma Phys...
Entropy, Software Quality, and Innovation (presented at Princeton Plasma Phys...
 

Recommendations assumptions