This deck was prepared for educational purpose and has no association with Netflix in anyway.
In case you want to know more, visit playflix.carrd.co or reach out at vagadro@gmail.com
The goal of a recommender system is to predict the degree to which a user will like or dislike a set of items, such as movies or TV shows.
Most recommender systems use a combination of different approaches, but broadly speaking there are three different methods that can be used: Content analysis, Social recommendations and Collaborative filtering.
A recommender system or a recommendation system is a subclass of information filtering systems that seeks to predict the "rating" or "preference" a user would give to an item. (Wiki)
The goal of a Recommender System is to generate meaningful recommendations to a collection of users for items or products that might interest them. (Melville, Sindhwani)
Recommender systems reduce the information/choice overload by estimating the relevance
The goal of a recommender system is to predict the degree to which a user will like or dislike a set of items, such as movies or TV shows.
Most recommender systems use a combination of different approaches, but broadly speaking there are three different methods that can be used: Content analysis, Social recommendations and Collaborative filtering.
A recommender system or a recommendation system is a subclass of information filtering systems that seeks to predict the "rating" or "preference" a user would give to an item. (Wiki)
The goal of a Recommender System is to generate meaningful recommendations to a collection of users for items or products that might interest them. (Melville, Sindhwani)
Recommender systems reduce the information/choice overload by estimating the relevance
Product Review of Netflix by Chisom Dom-Anyanwu.pdfChisomDomAnyanwu
I’m excited to present to you today my most recent work as a product manager — a thorough review of the Netflix Movie Streaming Application.
On doing this I discovered a problem that users have with the application: an immersive Comment Section feature. Users have expressed their interest in wanting a vital component — the ability to interact with other viewers through comments. Users argue that having a comment section within Netflix itself would enhance the viewing experience and foster a sense of community among its subscribers.
A comment section on Netflix can significantly boost business value and customer satisfaction. It fosters a sense of community, encourages word-of-mouth marketing, and allows users to share their thoughts on specific movies or TV shows. This can lead to personalized recommendations, improved customer satisfaction, and audience insights. The comment section also provides valuable audience insights, allowing Netflix to understand viewer preferences, identify trends, and make data-driven decisions about content library and future productions. Additionally, an integrated comment section within the Netflix platform provides a competitive advantage, providing a seamless and convenient space for users to engage without leaving the platform, potentially increasing customer loyalty.
As a passionate advocate for seamless user experiences and constant improvement, I decided to research and recommend solutions to this problem. #Netflix has undeniably revolutionized how we consume entertainment, captivating millions with its diverse content library and personalized recommendations. However, every great product can benefit from iterative enhancements, and that’s precisely what I set out to achieve.
User Research. Do or Do Not? How to design better products by understanding u...Borrys Hasian
To understand users, and get answers to your hypotheses, it's critical to pick the right user research method. Each answers different type of questions or hypotheses.
Basics of contributing to an open source project - from the first Linux Learners Day at LinuxCon 2011
http://events.linuxfoundation.org/events/linuxcon/student-program
Presentation by BBC Head of Audience Experience & Usability, Jonathan Hassell and Chris Rourke, MD of User Vision on the benefits of usability and accessibility research for the web and other digital platforms. Presented at Internet World, London, April 2009.
Interactive Recommender Systems with Netflix and SpotifyChris Johnson
Interactive recommender systems enable the user to steer the received recommendations in the desired direction through explicit interaction with the system. In the larger ecosystem of recommender systems used on a website, it is positioned between a lean-back recommendation experience and an active search for a specific piece of content. Besides this aspect, we will discuss several parts that are especially important for interactive recommender systems, including the following: design of the user interface and its tight integration with the algorithm in the back-end; computational efficiency of the recommender algorithm; as well as choosing the right balance between exploiting the feedback from the user as to provide relevant recommendations, and enabling the user to explore the catalog and steer the recommendations in the desired direction.
In particular, we will explore the field of interactive video and music recommendations and their application at Netflix and Spotify. We outline some of the user-experiences built, and discuss the approaches followed to tackle the various aspects of interactive recommendations. We present our insights from user studies and A/B tests.
The tutorial targets researchers and practitioners in the field of recommender systems, and will give the participants a unique opportunity to learn about the various aspects of interactive recommender systems in the video and music domain. The tutorial assumes familiarity with the common methods of recommender systems.
by Harald Steck (Netflix Inc., US), Roelof van Zwol (Netflix Inc., US) and Chris Johnson (Spotify Inc., US)
Slides of the tutorial on interactive recommender systems at the 2015 conference on Recommender Systems (RecSys).
Interactive recommender systems enable the user to steer the received recommendations in the desired direction through explicit interaction with the system. In the larger ecosystem of recommender systems used on a website, it is positioned between a lean-back recommendation experience and an active search for a specific piece of content. Besides this aspect, we will discuss several parts that are especially important for interactive recommender systems, including the following: design of the user interface and its tight integration with the algorithm in the back-end; computational efficiency of the recommender algorithm; as well as choosing the right balance between exploiting the feedback from the user as to provide relevant recommendations, and enabling the user to explore the catalog and steer the recommendations in the desired direction.
In particular, we will explore the field of interactive video and music recommendations and their application at Netflix and Spotify. We outline some of the user-experiences built, and discuss the approaches followed to tackle the various aspects of interactive recommendations. We present our insights from user studies and A/B tests.
The tutorial targets researchers and practitioners in the field of recommender systems, and will give the participants a unique opportunity to learn about the various aspects of interactive recommender systems in the video and music domain. The tutorial assumes familiarity with the common methods of recommender systems.
DATE: Wednesday, Sept 16, 2015, 11:00-12:30
Designing with your ears (or how to ensure your product gets used)Arthur Bodolec
Watch the presentation on Youtube here: https://www.youtube.com/watch?v=dSkuKDyQOh8
When building a new product or designing a new feature you always have a voice in the back of your mind whispering things such as: What if no one uses it? What if nobody really understands the value of what I am building? What if that thing I am designing becomes a total flop?
This presentation will give you simple and low time consuming techniques to ensure your product gets used. I will tell you how to find people to talk to, how to gather user stories to make sure you are designing the right features and a couple of ways to test you product.
Some feedback from the startup I gave the talk to:
"It was gold. Arthur was generous and giving everything away."
"Many easy-to-implement tips and nice “real world” examples :)"
Please give me some feedback and send me your questions at @abrodo on Twitter
Product Review of Netflix by Chisom Dom-Anyanwu.pdfChisomDomAnyanwu
I’m excited to present to you today my most recent work as a product manager — a thorough review of the Netflix Movie Streaming Application.
On doing this I discovered a problem that users have with the application: an immersive Comment Section feature. Users have expressed their interest in wanting a vital component — the ability to interact with other viewers through comments. Users argue that having a comment section within Netflix itself would enhance the viewing experience and foster a sense of community among its subscribers.
A comment section on Netflix can significantly boost business value and customer satisfaction. It fosters a sense of community, encourages word-of-mouth marketing, and allows users to share their thoughts on specific movies or TV shows. This can lead to personalized recommendations, improved customer satisfaction, and audience insights. The comment section also provides valuable audience insights, allowing Netflix to understand viewer preferences, identify trends, and make data-driven decisions about content library and future productions. Additionally, an integrated comment section within the Netflix platform provides a competitive advantage, providing a seamless and convenient space for users to engage without leaving the platform, potentially increasing customer loyalty.
As a passionate advocate for seamless user experiences and constant improvement, I decided to research and recommend solutions to this problem. #Netflix has undeniably revolutionized how we consume entertainment, captivating millions with its diverse content library and personalized recommendations. However, every great product can benefit from iterative enhancements, and that’s precisely what I set out to achieve.
User Research. Do or Do Not? How to design better products by understanding u...Borrys Hasian
To understand users, and get answers to your hypotheses, it's critical to pick the right user research method. Each answers different type of questions or hypotheses.
Basics of contributing to an open source project - from the first Linux Learners Day at LinuxCon 2011
http://events.linuxfoundation.org/events/linuxcon/student-program
Presentation by BBC Head of Audience Experience & Usability, Jonathan Hassell and Chris Rourke, MD of User Vision on the benefits of usability and accessibility research for the web and other digital platforms. Presented at Internet World, London, April 2009.
Interactive Recommender Systems with Netflix and SpotifyChris Johnson
Interactive recommender systems enable the user to steer the received recommendations in the desired direction through explicit interaction with the system. In the larger ecosystem of recommender systems used on a website, it is positioned between a lean-back recommendation experience and an active search for a specific piece of content. Besides this aspect, we will discuss several parts that are especially important for interactive recommender systems, including the following: design of the user interface and its tight integration with the algorithm in the back-end; computational efficiency of the recommender algorithm; as well as choosing the right balance between exploiting the feedback from the user as to provide relevant recommendations, and enabling the user to explore the catalog and steer the recommendations in the desired direction.
In particular, we will explore the field of interactive video and music recommendations and their application at Netflix and Spotify. We outline some of the user-experiences built, and discuss the approaches followed to tackle the various aspects of interactive recommendations. We present our insights from user studies and A/B tests.
The tutorial targets researchers and practitioners in the field of recommender systems, and will give the participants a unique opportunity to learn about the various aspects of interactive recommender systems in the video and music domain. The tutorial assumes familiarity with the common methods of recommender systems.
by Harald Steck (Netflix Inc., US), Roelof van Zwol (Netflix Inc., US) and Chris Johnson (Spotify Inc., US)
Slides of the tutorial on interactive recommender systems at the 2015 conference on Recommender Systems (RecSys).
Interactive recommender systems enable the user to steer the received recommendations in the desired direction through explicit interaction with the system. In the larger ecosystem of recommender systems used on a website, it is positioned between a lean-back recommendation experience and an active search for a specific piece of content. Besides this aspect, we will discuss several parts that are especially important for interactive recommender systems, including the following: design of the user interface and its tight integration with the algorithm in the back-end; computational efficiency of the recommender algorithm; as well as choosing the right balance between exploiting the feedback from the user as to provide relevant recommendations, and enabling the user to explore the catalog and steer the recommendations in the desired direction.
In particular, we will explore the field of interactive video and music recommendations and their application at Netflix and Spotify. We outline some of the user-experiences built, and discuss the approaches followed to tackle the various aspects of interactive recommendations. We present our insights from user studies and A/B tests.
The tutorial targets researchers and practitioners in the field of recommender systems, and will give the participants a unique opportunity to learn about the various aspects of interactive recommender systems in the video and music domain. The tutorial assumes familiarity with the common methods of recommender systems.
DATE: Wednesday, Sept 16, 2015, 11:00-12:30
Designing with your ears (or how to ensure your product gets used)Arthur Bodolec
Watch the presentation on Youtube here: https://www.youtube.com/watch?v=dSkuKDyQOh8
When building a new product or designing a new feature you always have a voice in the back of your mind whispering things such as: What if no one uses it? What if nobody really understands the value of what I am building? What if that thing I am designing becomes a total flop?
This presentation will give you simple and low time consuming techniques to ensure your product gets used. I will tell you how to find people to talk to, how to gather user stories to make sure you are designing the right features and a couple of ways to test you product.
Some feedback from the startup I gave the talk to:
"It was gold. Arthur was generous and giving everything away."
"Many easy-to-implement tips and nice “real world” examples :)"
Please give me some feedback and send me your questions at @abrodo on Twitter
EASY TUTORIAL OF HOW TO USE CAPCUT BY: FEBLESS HERNANEFebless Hernane
CapCut is an easy-to-use video editing app perfect for beginners. To start, download and open CapCut on your phone. Tap "New Project" and select the videos or photos you want to edit. You can trim clips by dragging the edges, add text by tapping "Text," and include music by selecting "Audio." Enhance your video with filters and effects from the "Effects" menu. When you're happy with your video, tap the export button to save and share it. CapCut makes video editing simple and fun for everyone!
White wonder, Work developed by Eva TschoppMansi Shah
White Wonder by Eva Tschopp
A tale about our culture around the use of fertilizers and pesticides visiting small farms around Ahmedabad in Matar and Shilaj.
Hello everyone! I am thrilled to present my latest portfolio on LinkedIn, marking the culmination of my architectural journey thus far. Over the span of five years, I've been fortunate to acquire a wealth of knowledge under the guidance of esteemed professors and industry mentors. From rigorous academic pursuits to practical engagements, each experience has contributed to my growth and refinement as an architecture student. This portfolio not only showcases my projects but also underscores my attention to detail and to innovative architecture as a profession.
Expert Accessory Dwelling Unit (ADU) Drafting ServicesResDraft
Whether you’re looking to create a guest house, a rental unit, or a private retreat, our experienced team will design a space that complements your existing home and maximizes your investment. We provide personalized, comprehensive expert accessory dwelling unit (ADU)drafting solutions tailored to your needs, ensuring a seamless process from concept to completion.
Connect Conference 2022: Passive House - Economic and Environmental Solution...TE Studio
Passive House: The Economic and Environmental Solution for Sustainable Real Estate. Lecture by Tim Eian of TE Studio Passive House Design in November 2022 in Minneapolis.
- The Built Environment
- Let's imagine the perfect building
- The Passive House standard
- Why Passive House targets
- Clean Energy Plans?!
- How does Passive House compare and fit in?
- The business case for Passive House real estate
- Tools to quantify the value of Passive House
- What can I do?
- Resources
2. The Problem Empathy Define Ideate
Prototype and
Test
Potential
Problems
Roadmap
Users find it difficult to choose/explore the right
content to watch and end up spending too much
time on searching content because of Netflix’s
overwhelming library and not so accurate
recommendation system
Target Personas
Validation
4 Netflix users were interviewed and 41 user
surveys were conducted to understand depth of
the problem
~49% users(mostly gen Z) do not
find the current recommendation
useful
~ 70% users follow
recommendations by family/friends,
generally shared verbally
~80% of users ( all age group)
suggested there should be a better
way to share recommendations in
Netflix which makes finding content
easy
Quick Watchers: people who do
not want to waste time searching
for content and stick to suggested
shows/recurrent content
Explorers: people who like to
explore new content to watch
3. Why NOW?
The Problem Empathy Define Ideate
Prototype and
Test
Potential
Problems
Roadmap
Potential Value Generated
For the Business
For Target Customers
Users will be able to find right content to watch on
the platform seamlessly without spending much time
Although Netflix leads the global streaming market
share, its projected growth has seen a drop of ~3%
in Q4 ‘21 which happened for the first time since 2015
Thus, since the content streaming market has become
extremely competitive due to entrance of other
players, Netflix has too come up with new features to
enhance user engagement for minimizing migration
and maximizing user acquisition
% of US Video Streaming Distribution
Netflix
Prime Video
Disney
Hulu
Other
Source: Nielsen, 2020
Search Experience
Streaming and content consumption
= Revenue
Improved search experience will drive Customer
satisfaction and in turn will lead to increase in revenue
4. Solutions
1 2 3
Content Rating System:
Create rating system for
content on Netflix to help user
choose content as per the
ratings
Play Random:
Create a "Random Play" button
on Netflix user page which would
randomly play content as per
user's streaming history and
analytics
Custom Playlists:
Many users want to explore
content beyond Netflix's
recommendations but they do
not have option to. Playlists will
help users to find movies/shows
depending on there likes and
dislikes by searching for a playlist.
Solution Prioritization
Solution Impact (I) Confidence (C) Effort (E) Score = I*C/E
Play Random Low Low Low Low
Rating System Medium Medium Low Medium
Custom Playlist High High High High
Customer Playlist, which supports
user/platform interaction has a high
priority score and gives more
confidence to user to decide to choose
what to watch in a seamless manner
Final Solution
Empathy Define Ideate
Prototype and
Test
Potential
Problems
Roadmap
5. Solution Details Empathy Define Ideate
Prototype and
Test
Potential
Problems
Roadmap
Hrithik wants to watch a
Brad Pitt movie while
having lunch but cant
decide which one to
watch
Searches “Brad Pitt” but
gets confused amongst
ton of options
Searches for Brad Pitt’s
movies on google search
and decides to watch
“Furry”
Searches “Furry” on
Netflix and finds out
movie is not listed on
Netflix
Frustrated, ends up
watching “Friends”
again
Searches “Brad Pitt”,
gets playlist options like
“top 5 Brad Pitt Movies”
Quickly looks at # of
shares and Ratings of
playlists
Confidently selects one,
adds into its My List
section by pressing +
button
Happily watches movie
with coke and popcorns
Proposed Solution
Current Process
6. Solution Desirability Empathy Define Ideate
Prototype and
Test
Potential
Problems
Roadmap
Landing Page describing solution offering and value proposition in detail: Netflix Playlist
Solution Analysis
160 Page views with 63.8 %
Bounce rate
5 min 21 sec avg. session
duration
89% of interested users were
positive about the idea and felt
the solution will help search
content better and faster
~72% of interested users are
high likely to recommend this
feature
7. Success Metrics Empathy Define Ideate
Prototype and
Test
Potential
Problems
Roadmap
Reach Activation Engagement Business Specific
Playlist Usage %
# users used playlist
(added or created)
Total number of Netflix
users
Feature Activation %
# of users using playlist
within 15/30/45 days
Total number of Netflix
users
% Engagement per
user
# of playlists which are
shared
Total number of playlists
created by user
Avg. streaming hour
change per user
(before vs after
product launch)
Avg. streaming hour
change per content
(before vs after
product launch)
8. Potential Pitfalls Empathy Define Ideate
Prototype and
Test
Potential
Problems
Roadmap
Multiple playlist with
same title
Unavailability of share
option in Desktop
version
Mitigate by creating
tutorials (within app,
YouTube, Instagram) on
how to efficiently use the
feature
This in turn will also drive
users towards feature
discovery and awareness
Mitigated by adding creator
username against the
playlist title.
For e.g.
Top 5 Brad Pitt by vagadro
Top 5 Brad Pitt by whamybear
Share feature to be a part
of Mobile version only in
short term (as is current)
For desktop version
people will have to use
search and add feature to
add playlist
High Learning Curve
9. Roadmap Empathy Define Ideate
Prototype and
Test
Potential
Problems
Roadmap
Phase I- Test Phase II- Rollout Phase III- Improve
Test in a single Geography
- This will ensure people
sharing a playlist will see the
same content
Test product on Mobile
- Since share feature is only
available on mobile version
currently
Full Rollout
- Open feature for all
countries
Launch on Desktop
- Launch on Desktop to
ensure maximum
engagement
Metrics Analysis
- Monitor country specific
metrics to check usability
Product analysis
- Identify pain points and try
to solve aiming at
continuous product
improvement
Introduce Rewards
- Launch rewards program.
E.g: 1 month free
subscription for user’s
playlist with maximum
shares