SlideShare a Scribd company logo
Image: Akritasa (cc)
Interaction designers

versus algorithms
@gilescolborne
No matter how cool

your user interface is,

it would be better

if there were less of it.
Alan Cooper
Algorithms and artificial intelligence give us the power to
simplify interactions.
What does that mean for interaction design practice?
Spotify’s Discover
Weekly is one of it’s most
delightful and valuable
features, according to
users I’ve spoken to.
But it’s a playlist. If you
were the interaction
designer, what might
you have contributed?
Stuff that the user wants
goes here.
Maybe this sketch?
It looks like the real
work was being done by
the engineer who wrote
the algorithm.
Is that changing the
nature of interaction
design?
What about something
like this. I know people
who’ve spent a lot of
time figuring out how to
help users move through
this inofmation.
How might this be
redesigned?
Book me an off peak return from
Bath to London for next Tuesday
with a seat reservation on the way
back at 4:30.
Would you like to add a Zone
1-5 Travelcard for £5.80?
Yes plz
That comes to £78.20 including
booking fee. Want to go ahead?
Trainline BookingMenu My tickets
OK
Chatbots can answer the
same questions in a
natural way that feels
familiar to users.
The interaction here is
with the collection of
natural language
algorithms beneath the
hood.
Here is exactly
what you need
right now
So now I’m wondering,
how much design will get
displaced by data
scientists and algorithm
engineers.
Ariel Luenberger
Let’s imagine we’re
designing for a bus
company.
This chap needs to know
‘where’s my bus?’. How
could an algorithm help?
Well, you need to begin
with data…
Imagine we have layers of data. We know when buses were late,
what the weather was like, locations of roadworks, traffic and
so on. We could use it to predict how late your bus will be.
Machine learning
is not magic
it’s engineering
Well, if you come up with an idea, you need to know enough
about algorithms to have a sensible conversation with an
engineer. Here are the basics of that conversation…
Here’s the task. You have input data (weather, traffic patterns
and so on), an algorithm, and some outputs (is the bus late?).
You need to know what kind of output is useful to the user. Is it
enough to say ‘late?’ Or do you need to give a precise delay? More
detailed output means a more complex engineering challenge.
The engineer chooses the algorithm and trains it by showing it
sample inputs (weather, traffic, etc.) and known outputs (when
the bus actually arrived) until the algorithm can fit inputs and
ouputs.
If your data is inaccurate (for instance the GPS doesn’t work well
in some areas) then your algorithm will learn to make inaccurate
predictions. So you need to be able to judge data quality.
If your problem is complex and relies on lots of different data
sets, then you’re going to need more training data. That can be
hard to get hold of. Engineers will get nervous if you keep adding
data sets. So which ones do you really need?
High varianceHigh bias
If you don’t have an accurate algorithm, you can at least choose
how to be wrong. Biased consistantly, variable around an
average. In our case it’s better to be biased (towards saying the
bus will be on time) rather than to be right on average.
If the data in the layers is unnecessarily complex then the
algorithm may be unreliable, too. So rather than throw raw data
at the algorithm, it’s a good idea to simplify whats in each data
set.
Do you need to know precise rainfall times, hour by hour, or just
‘did it rain in the morning’. That affects how much data is in your
data set. Sometimes less data gives better accuracy - like turning
up the contrast on a scanned image of text to make it more legible.
At the end of this you’ll have a trained algorithm that delivers the
information you want based on the data you have. But it may still
not be accurate enough. So you’ll need a closed beta or a live
service with a feedback loop to keep up the training.
Ariel Luenberger
So we built a prediction
machine. All the way
through there’s a
dialogue between
designer and engineer
about what’s possible
and how to present it.
Perhaps as tools and APIs proliferate, designers will take on the
job of training algorithms. But the real place designers add value
is in defining what the outputs should be and how they’re
presented to the user.
If you wrap up your
recommendations in
an interface that
promises human-
like interactions
with less than
human manners,
then people will
revolt.
Interfaces like this
offer suggestions in
a subtler, less pushy
way. Designing the
etiquette of
suggestions will be
important in next
generation
interaction design.
Book me an off peak return from
Bath to London for next Tuesday
with a seat reservation on the way
back at 4:30.
Would you like to add a Zone
1-5 Travelcard for £5.80?
Yes plz
That comes to £78.20 including
booking fee. Want to go ahead?
Trainline BookingMenu My tickets
OK
If you’re dealing with
natural language
interfaces, a lot of the
same rules apply.
You need a set of
training data -
transcripts of call
customer service
conversations.
You may need simplify
that data - for instance
by looking for the
successulf
conversations.
And you need to think
how to set users’
expectations about
talking to a bot.
The adventure game
Lost Pig has you telling
an Orc what to do. So you
know to keep it simple
and expect errors.
It’s cute, has personality
and humour, and serves
an engineering purpose.
You’ll need to map out
conversations as
flowcharts. But there’s a
lot of copywriting you’ll
need to do around those
flows to make it feel
natural. For instance,
you may want to give a
long answer the first
time someone asks a
question and then a
shorter summary the
second time.
Book me an off peak return from
Bath to London for next Tuesday
with a seat reservation on the way
back at 4:30.
Would you like to add a Zone
1-5 Travelcard for £5.80?
Yes plz
That comes to £78.20 including
booking fee. Want to go ahead?
Trainline BookingMenu My tickets
OK
I’ve always looked to
human conversation
patterns to figure out
how to solve interaction
design problems.
Now I find that
understanding human to
human conversation is
core design knowledge.
And what about Discover
Weekly? Well, a large
part of the design work
there was about
understanding how to
package up the service.
Playlists were familiar.
And limiting the size of
the playlist gave it a feel
of a mix tape from a
friend, rather than a
data dump from an
algorithm.
The designers made it
feel elegant and
approachable.
So our core skills are still
important. There’s a rich
future for interaction
design.
But the journey to
evolve our practice and
knowledge is just
begining.
Image: Akritasa (cc)
Thank you
@gilescolborne

More Related Content

Similar to Interaction designers vs algorithms (20)

PDF
Design for complexity
Lextant
 
PDF
What are machines learning? How might that impact design?
Andreas Wolters
 
PPT
Make Tools
Victor Lombardi
 
PDF
Web valley talk - usability, visualization and mobile app development
Eamonn Maguire
 
PPT
Big Data, Smart Algorithms, and Market Power - A Computer Scientist’s Perspec...
Heiko Paulheim
 
PPTX
Machine learning for designers masterclass
Jonah Burlingame
 
PDF
Push conference 2018 key takeaways
Justin Crowell
 
PDF
Hybrid Publishing Design Methods For Technical Books
Technological Ecosystems for Enhancing Multiculturality
 
PPTX
Mind the Gap: Bridging the Research–Practice Divide
Tony Russell-Rose
 
PDF
Practical Considerations for Interactive AI: Robustness, Privacy, Fairness, T...
Tom Diethe
 
PDF
Principles of Interactive Design
Karen Krull
 
PPTX
Interaction design: desiging user interfaces for digital products
David Little
 
PDF
Designing Interfaces Second Edition Jenifer Tidwell
gikovadzaky
 
PDF
UX for Artificial Intelligence / UXcamp Europe '17 / Berlin / Jan Korsanke
Jan Korsanke
 
PDF
Foundations of IA
Liam Tullberg
 
PDF
Foundations of IA - World IA Day
Nomensa
 
PDF
ICS3211_lecture 04 2023.pdf
Vanessa Camilleri
 
PPS
CS101- Introduction to Computing- Lecture 34
Bilal Ahmed
 
PPT
Owning the Interaction in Dynamic Environments
guestf4f7a4b38
 
PPT
Owning the Interaction in Dynamic Environments
Fergus Roche
 
Design for complexity
Lextant
 
What are machines learning? How might that impact design?
Andreas Wolters
 
Make Tools
Victor Lombardi
 
Web valley talk - usability, visualization and mobile app development
Eamonn Maguire
 
Big Data, Smart Algorithms, and Market Power - A Computer Scientist’s Perspec...
Heiko Paulheim
 
Machine learning for designers masterclass
Jonah Burlingame
 
Push conference 2018 key takeaways
Justin Crowell
 
Hybrid Publishing Design Methods For Technical Books
Technological Ecosystems for Enhancing Multiculturality
 
Mind the Gap: Bridging the Research–Practice Divide
Tony Russell-Rose
 
Practical Considerations for Interactive AI: Robustness, Privacy, Fairness, T...
Tom Diethe
 
Principles of Interactive Design
Karen Krull
 
Interaction design: desiging user interfaces for digital products
David Little
 
Designing Interfaces Second Edition Jenifer Tidwell
gikovadzaky
 
UX for Artificial Intelligence / UXcamp Europe '17 / Berlin / Jan Korsanke
Jan Korsanke
 
Foundations of IA
Liam Tullberg
 
Foundations of IA - World IA Day
Nomensa
 
ICS3211_lecture 04 2023.pdf
Vanessa Camilleri
 
CS101- Introduction to Computing- Lecture 34
Bilal Ahmed
 
Owning the Interaction in Dynamic Environments
guestf4f7a4b38
 
Owning the Interaction in Dynamic Environments
Fergus Roche
 

More from cxpartners (20)

PDF
Chi briding the relevance gap
cxpartners
 
PDF
Putting people at the centre of design at the samaritans
cxpartners
 
PDF
cxpartners customer centricity
cxpartners
 
PDF
Designing Without Compromise
cxpartners
 
PDF
Practical Steps in Determining Your Product Vision (Product Tank Bristol - Oc...
cxpartners
 
PDF
How to do the work you want to do - AKA neglect selling skills at your peril!...
cxpartners
 
PDF
Customer Driven Digital Transformation
cxpartners
 
PDF
UX vs Artificial Intelligence
cxpartners
 
PDF
Research analysis: getting more from your data
cxpartners
 
PDF
Transforming Care in Bristol
cxpartners
 
PDF
Beyond the touch screen - better accessibility for mobile apps
cxpartners
 
PDF
Co design (NUX4)
cxpartners
 
PDF
How to ask a question
cxpartners
 
PDF
UX Leadership
cxpartners
 
PDF
Photo ux nux 061014
cxpartners
 
PDF
Photo content strategy (James Chudley, cxpartners)
cxpartners
 
PDF
Psychology and the Perfect Design by @mrjoe
cxpartners
 
PDF
How Rapid Feedback improves the design process (Luke Jones, cxpartners)
cxpartners
 
PDF
How to build a failsafe mobile usability testing set up
cxpartners
 
PDF
Exploring the user experience through ethnography (Anna Wilkie, cxpartners)
cxpartners
 
Chi briding the relevance gap
cxpartners
 
Putting people at the centre of design at the samaritans
cxpartners
 
cxpartners customer centricity
cxpartners
 
Designing Without Compromise
cxpartners
 
Practical Steps in Determining Your Product Vision (Product Tank Bristol - Oc...
cxpartners
 
How to do the work you want to do - AKA neglect selling skills at your peril!...
cxpartners
 
Customer Driven Digital Transformation
cxpartners
 
UX vs Artificial Intelligence
cxpartners
 
Research analysis: getting more from your data
cxpartners
 
Transforming Care in Bristol
cxpartners
 
Beyond the touch screen - better accessibility for mobile apps
cxpartners
 
Co design (NUX4)
cxpartners
 
How to ask a question
cxpartners
 
UX Leadership
cxpartners
 
Photo ux nux 061014
cxpartners
 
Photo content strategy (James Chudley, cxpartners)
cxpartners
 
Psychology and the Perfect Design by @mrjoe
cxpartners
 
How Rapid Feedback improves the design process (Luke Jones, cxpartners)
cxpartners
 
How to build a failsafe mobile usability testing set up
cxpartners
 
Exploring the user experience through ethnography (Anna Wilkie, cxpartners)
cxpartners
 
Ad

Recently uploaded (20)

PPTX
Chapter 2-3.pptxnsnsnsnsnsjsjsjsjejeusuejsjsj
hibaaqabdirisaaq331
 
PDF
ARChitec-BUILDING-UTILITIES-2-PART-5.pdf
IzzyBaniquedBusto
 
PDF
Plastic Foam as eco-friendly product in interiors
Disha Agrawal
 
PPTX
7psofmarketingandbranding-250114091831-cba08a7c (1).pptx
jamescarllfelomino6
 
PPTX
Graphic_Design_Pjjjjjjjjjjjjjjjresentation.pptx
kumarsahil80682
 
PPTX
DEVELOPING-PARAGRAPHS.pptx-developing...
rania680036
 
PPT
1744066yaar kya hai ye bolo not nice 4.ppt
preethikavarsha
 
PPTX
811109685-CS3401-Algorithms-Unit-IV.pptx
archu26
 
PDF
EY-emeia-fso-assurance-viewpoint-technology (1).pdf
INKPPT
 
PPTX
Chapter 1-1.pptx hwhahaiaiautsfzjakaiwueysuua
hibaaqabdirisaaq331
 
PDF
SS27 Men's Fashion Trend Book Peclers Paris
Peclers Paris
 
PDF
placemaking 10 principles bY Berkley group
Radhika525487
 
PDF
Ecowood.pdf | Tranquil Global Acoustics India
tranquil01
 
DOCX
Redefining Master Plans for creating sustainable cities-Jharkhand Conference...
JIT KUMAR GUPTA
 
PPTX
sistem teknologi yang di desain untuk mahasiswa dan dosen agar memudahkan mer...
gamesonlya2rj
 
PPTX
presentation prsentation presentation presentation
ssun76691
 
POTX
khsakhdjsahfsdfkjehfewfjxmxkvskghjdkskjhfdsjkhf.potx
NovitaYuliani4
 
PDF
AI Intervention in Design & Content Creation
YellowSlice1
 
PDF
CS6801-MULTI-CORE-ARCHITECTURE-AND-PROGRAMMING_watermark.pdf
SriRanjani60
 
PPTX
Urban design is a huge concept when it comes to planning.
IshikaPanchal11
 
Chapter 2-3.pptxnsnsnsnsnsjsjsjsjejeusuejsjsj
hibaaqabdirisaaq331
 
ARChitec-BUILDING-UTILITIES-2-PART-5.pdf
IzzyBaniquedBusto
 
Plastic Foam as eco-friendly product in interiors
Disha Agrawal
 
7psofmarketingandbranding-250114091831-cba08a7c (1).pptx
jamescarllfelomino6
 
Graphic_Design_Pjjjjjjjjjjjjjjjresentation.pptx
kumarsahil80682
 
DEVELOPING-PARAGRAPHS.pptx-developing...
rania680036
 
1744066yaar kya hai ye bolo not nice 4.ppt
preethikavarsha
 
811109685-CS3401-Algorithms-Unit-IV.pptx
archu26
 
EY-emeia-fso-assurance-viewpoint-technology (1).pdf
INKPPT
 
Chapter 1-1.pptx hwhahaiaiautsfzjakaiwueysuua
hibaaqabdirisaaq331
 
SS27 Men's Fashion Trend Book Peclers Paris
Peclers Paris
 
placemaking 10 principles bY Berkley group
Radhika525487
 
Ecowood.pdf | Tranquil Global Acoustics India
tranquil01
 
Redefining Master Plans for creating sustainable cities-Jharkhand Conference...
JIT KUMAR GUPTA
 
sistem teknologi yang di desain untuk mahasiswa dan dosen agar memudahkan mer...
gamesonlya2rj
 
presentation prsentation presentation presentation
ssun76691
 
khsakhdjsahfsdfkjehfewfjxmxkvskghjdkskjhfdsjkhf.potx
NovitaYuliani4
 
AI Intervention in Design & Content Creation
YellowSlice1
 
CS6801-MULTI-CORE-ARCHITECTURE-AND-PROGRAMMING_watermark.pdf
SriRanjani60
 
Urban design is a huge concept when it comes to planning.
IshikaPanchal11
 
Ad

Interaction designers vs algorithms

  • 1. Image: Akritasa (cc) Interaction designers
 versus algorithms @gilescolborne
  • 2. No matter how cool
 your user interface is,
 it would be better
 if there were less of it. Alan Cooper Algorithms and artificial intelligence give us the power to simplify interactions. What does that mean for interaction design practice?
  • 3. Spotify’s Discover Weekly is one of it’s most delightful and valuable features, according to users I’ve spoken to. But it’s a playlist. If you were the interaction designer, what might you have contributed?
  • 4. Stuff that the user wants goes here. Maybe this sketch? It looks like the real work was being done by the engineer who wrote the algorithm. Is that changing the nature of interaction design?
  • 5. What about something like this. I know people who’ve spent a lot of time figuring out how to help users move through this inofmation. How might this be redesigned?
  • 6. Book me an off peak return from Bath to London for next Tuesday with a seat reservation on the way back at 4:30. Would you like to add a Zone 1-5 Travelcard for £5.80? Yes plz That comes to £78.20 including booking fee. Want to go ahead? Trainline BookingMenu My tickets OK Chatbots can answer the same questions in a natural way that feels familiar to users. The interaction here is with the collection of natural language algorithms beneath the hood.
  • 7. Here is exactly what you need right now So now I’m wondering, how much design will get displaced by data scientists and algorithm engineers.
  • 8. Ariel Luenberger Let’s imagine we’re designing for a bus company. This chap needs to know ‘where’s my bus?’. How could an algorithm help? Well, you need to begin with data…
  • 9. Imagine we have layers of data. We know when buses were late, what the weather was like, locations of roadworks, traffic and so on. We could use it to predict how late your bus will be.
  • 10. Machine learning is not magic it’s engineering Well, if you come up with an idea, you need to know enough about algorithms to have a sensible conversation with an engineer. Here are the basics of that conversation…
  • 11. Here’s the task. You have input data (weather, traffic patterns and so on), an algorithm, and some outputs (is the bus late?).
  • 12. You need to know what kind of output is useful to the user. Is it enough to say ‘late?’ Or do you need to give a precise delay? More detailed output means a more complex engineering challenge.
  • 13. The engineer chooses the algorithm and trains it by showing it sample inputs (weather, traffic, etc.) and known outputs (when the bus actually arrived) until the algorithm can fit inputs and ouputs.
  • 14. If your data is inaccurate (for instance the GPS doesn’t work well in some areas) then your algorithm will learn to make inaccurate predictions. So you need to be able to judge data quality.
  • 15. If your problem is complex and relies on lots of different data sets, then you’re going to need more training data. That can be hard to get hold of. Engineers will get nervous if you keep adding data sets. So which ones do you really need?
  • 16. High varianceHigh bias If you don’t have an accurate algorithm, you can at least choose how to be wrong. Biased consistantly, variable around an average. In our case it’s better to be biased (towards saying the bus will be on time) rather than to be right on average.
  • 17. If the data in the layers is unnecessarily complex then the algorithm may be unreliable, too. So rather than throw raw data at the algorithm, it’s a good idea to simplify whats in each data set.
  • 18. Do you need to know precise rainfall times, hour by hour, or just ‘did it rain in the morning’. That affects how much data is in your data set. Sometimes less data gives better accuracy - like turning up the contrast on a scanned image of text to make it more legible.
  • 19. At the end of this you’ll have a trained algorithm that delivers the information you want based on the data you have. But it may still not be accurate enough. So you’ll need a closed beta or a live service with a feedback loop to keep up the training.
  • 20. Ariel Luenberger So we built a prediction machine. All the way through there’s a dialogue between designer and engineer about what’s possible and how to present it.
  • 21. Perhaps as tools and APIs proliferate, designers will take on the job of training algorithms. But the real place designers add value is in defining what the outputs should be and how they’re presented to the user.
  • 22. If you wrap up your recommendations in an interface that promises human- like interactions with less than human manners, then people will revolt.
  • 23. Interfaces like this offer suggestions in a subtler, less pushy way. Designing the etiquette of suggestions will be important in next generation interaction design.
  • 24. Book me an off peak return from Bath to London for next Tuesday with a seat reservation on the way back at 4:30. Would you like to add a Zone 1-5 Travelcard for £5.80? Yes plz That comes to £78.20 including booking fee. Want to go ahead? Trainline BookingMenu My tickets OK If you’re dealing with natural language interfaces, a lot of the same rules apply.
  • 25. You need a set of training data - transcripts of call customer service conversations. You may need simplify that data - for instance by looking for the successulf conversations.
  • 26. And you need to think how to set users’ expectations about talking to a bot. The adventure game Lost Pig has you telling an Orc what to do. So you know to keep it simple and expect errors. It’s cute, has personality and humour, and serves an engineering purpose.
  • 27. You’ll need to map out conversations as flowcharts. But there’s a lot of copywriting you’ll need to do around those flows to make it feel natural. For instance, you may want to give a long answer the first time someone asks a question and then a shorter summary the second time.
  • 28. Book me an off peak return from Bath to London for next Tuesday with a seat reservation on the way back at 4:30. Would you like to add a Zone 1-5 Travelcard for £5.80? Yes plz That comes to £78.20 including booking fee. Want to go ahead? Trainline BookingMenu My tickets OK I’ve always looked to human conversation patterns to figure out how to solve interaction design problems. Now I find that understanding human to human conversation is core design knowledge.
  • 29. And what about Discover Weekly? Well, a large part of the design work there was about understanding how to package up the service. Playlists were familiar. And limiting the size of the playlist gave it a feel of a mix tape from a friend, rather than a data dump from an algorithm.
  • 30. The designers made it feel elegant and approachable. So our core skills are still important. There’s a rich future for interaction design. But the journey to evolve our practice and knowledge is just begining.
  • 31. Image: Akritasa (cc) Thank you @gilescolborne