Tweet
Tweet

Slide 1

Slide 1 text

Designing Recommender Systems by Diana MacDonald // 12 Apr 2019 Designing Recommender Systems @DiDoesDigital

Slide 2

Slide 2 text

No content

Slide 3

Slide 3 text

No content

Slide 4

Slide 4 text

No content

Slide 5

Slide 5 text

Recommender systems Designing Recommender Systems @DiDoesDigital

Slide 6

Slide 6 text

Recommender systems Predict preferences Designing Recommender Systems @DiDoesDigital

Slide 7

Slide 7 text

Recommender systems Show relevant items Designing Recommender Systems @DiDoesDigital

Slide 8

Slide 8 text

Recommender systems Content discovery and decision making Designing Recommender Systems @DiDoesDigital

Slide 9

Slide 9 text

Credit: https:/ /medium.com/netflix-techblog/artwork-personalization-c589f074ad76

Slide 10

Slide 10 text

No content

Slide 11

Slide 11 text

No content

Slide 12

Slide 12 text

Recommenders are handy Designing Recommender Systems @DiDoesDigital

Slide 13

Slide 13 text

The problem Designing Recommender Systems @DiDoesDigital

Slide 14

Slide 14 text

The problem Plain English Designing Recommender Systems @DiDoesDigital

Slide 15

Slide 15 text

The problem UX design Designing Recommender Systems @DiDoesDigital

Slide 16

Slide 16 text

Designing Recommender Systems @DiDoesDigital Credit: https:/ /en.wikipedia.org/wiki/Root-mean-square_deviation
 Credit: https:/ /en.wikipedia.org/wiki/Matrix_factorization_(recommender_systems)
 Credit: https:/ /commons.wikimedia.org/wiki/File:Singular_value_decomposition_visualisation.svg

Slide 17

Slide 17 text

No content

Slide 18

Slide 18 text

I rarely think about looking for a job at another company Designing Recommender Systems @DiDoesDigital “ Agree

Slide 19

Slide 19 text

No content

Slide 20

Slide 20 text

No content

Slide 21

Slide 21 text

Designing Recommender Systems @DiDoesDigital

Slide 22

Slide 22 text

Designing recommender systems 1. Choosing outcomes 3. Improving over time 2. Design
 considerations Designing Recommender Systems @DiDoesDigital

Slide 23

Slide 23 text

Designing recommender systems 1. Choosing outcomes 3. Improving over time 2. Design
 considerations Designing Recommender Systems @DiDoesDigital

Slide 24

Slide 24 text

Choose outcomes What does success look like? Designing Recommender Systems @DiDoesDigital

Slide 25

Slide 25 text

Choose outcomes 1 of 4 / / Business impact Designing Recommender Systems @DiDoesDigital

Slide 26

Slide 26 text

No content

Slide 27

Slide 27 text

No content

Slide 28

Slide 28 text

Choose outcomes 2 of 4 / / Values Designing Recommender Systems @DiDoesDigital

Slide 29

Slide 29 text

How do you feel about your day at work? “

Slide 30

Slide 30 text

How do you feel about your day at work? “

Slide 31

Slide 31 text

Choose outcomes 3 of 4 / / Time to decision Designing Recommender Systems @DiDoesDigital

Slide 32

Slide 32 text

No content

Slide 33

Slide 33 text

Choose outcomes 4 of 4 / / Satisfaction Designing Recommender Systems @DiDoesDigital

Slide 34

Slide 34 text

No content

Slide 35

Slide 35 text

No content

Slide 36

Slide 36 text

Designing recommender systems 1. Choosing outcomes 3. Improving over time 2. Design
 considerations Designing Recommender Systems @DiDoesDigital

Slide 37

Slide 37 text

Design for trust Designing Recommender Systems @DiDoesDigital

Slide 38

Slide 38 text

Design for trust Social proof Designing Recommender Systems @DiDoesDigital

Slide 39

Slide 39 text

No content

Slide 40

Slide 40 text

Design for trust Labels & headings Designing Recommender Systems @DiDoesDigital

Slide 41

Slide 41 text

No content

Slide 42

Slide 42 text

No content

Slide 43

Slide 43 text

No content

Slide 44

Slide 44 text

No content

Slide 45

Slide 45 text

No content

Slide 46

Slide 46 text

Design for trust Fast and slow (recency and stability) Designing Recommender Systems @DiDoesDigital

Slide 47

Slide 47 text

No content

Slide 48

Slide 48 text

No content

Slide 49

Slide 49 text

No content

Slide 50

Slide 50 text

No content

Slide 51

Slide 51 text

Design for trust Transparency Designing Recommender Systems @DiDoesDigital

Slide 52

Slide 52 text

No content

Slide 53

Slide 53 text

No content

Slide 54

Slide 54 text

Design for experience Designing Recommender Systems @DiDoesDigital

Slide 55

Slide 55 text

Design for experience Diversity and serendipity Designing Recommender Systems @DiDoesDigital

Slide 56

Slide 56 text

No content

Slide 57

Slide 57 text

Design for experience Visual clarity Designing Recommender Systems @DiDoesDigital

Slide 58

Slide 58 text

Choosing an action

Slide 59

Slide 59 text

Choosing an action

Slide 60

Slide 60 text

Design for experience Data is not neutral Designing Recommender Systems @DiDoesDigital

Slide 61

Slide 61 text

No content

Slide 62

Slide 62 text

No content

Slide 63

Slide 63 text

No content

Slide 64

Slide 64 text

Designing recommender systems 1. Choosing outcomes 3. Improving over time 2. Design
 considerations Designing Recommender Systems @DiDoesDigital

Slide 65

Slide 65 text

Recommender techniques Content-based filtering Collaborative filtering Designing Recommender Systems @DiDoesDigital Knowledge based

Slide 66

Slide 66 text

Recommender techniques Content-based filtering Collaborative filtering Designing Recommender Systems @DiDoesDigital Knowledge based

Slide 67

Slide 67 text

Recommender techniques Content-based filtering Collaborative filtering Designing Recommender Systems @DiDoesDigital Knowledge based

Slide 68

Slide 68 text

Recommender techniques Content-based filtering Collaborative filtering Designing Recommender Systems @DiDoesDigital Knowledge based

Slide 69

Slide 69 text

Recommender techniques Content-based filtering Collaborative filtering Designing Recommender Systems @DiDoesDigital Knowledge based

Slide 70

Slide 70 text

Recommender techniques Content-based filtering Collaborative filtering Designing Recommender Systems @DiDoesDigital Knowledge based

Slide 71

Slide 71 text

Recommender techniques Content-based filtering Collaborative filtering Designing Recommender Systems @DiDoesDigital Knowledge based

Slide 72

Slide 72 text

Recommender techniques Hybrid filtering Designing Recommender Systems @DiDoesDigital

Slide 73

Slide 73 text

Hybridization Mixed Designing Recommender Systems @DiDoesDigital

Slide 74

Slide 74 text

No content

Slide 75

Slide 75 text

Feedback signals Positive and negative Designing Recommender Systems @DiDoesDigital

Slide 76

Slide 76 text

No content

Slide 77

Slide 77 text

No content

Slide 78

Slide 78 text

Feedback signals Implicit and explicit Designing Recommender Systems @DiDoesDigital

Slide 79

Slide 79 text

No content

Slide 80

Slide 80 text

No content

Slide 81

Slide 81 text

Without machine learning Designing Recommender Systems @DiDoesDigital

Slide 82

Slide 82 text

No content

Slide 83

Slide 83 text

No content

Slide 84

Slide 84 text

No content

Slide 85

Slide 85 text

4% started

Slide 86

Slide 86 text

46% skipped events Games and breaks Designing Recommender Systems @DiDoesDigital

Slide 87

Slide 87 text

Designing recommender systems 1. Choosing outcomes 3. Improving over time 2. Design
 considerations Designing Recommender Systems @DiDoesDigital

Slide 88

Slide 88 text

Learn more • https:/ /uxplanet.org/how-can-we-design-an-intelligent- recommender-engine-b9bb1db4d050 • https:/ /www.nngroup.com/articles/recommendation-expectations/ • https:/ /research.netflix.com/research-area/recommendations • https:/ /en.wikipedia.org/wiki/Recommender_system Designing Recommender Systems @DiDoesDigital

Slide 89

Slide 89 text

Designing Recommender Systems @DiDoesDigital Icons by Material Design Montserrat type by Julieta Ulanovsky Questions? Diana MacDonald | DiDoesDigital.com Pre-order on Amazon