Mind Reading - Understanding Recommender Systems

Slide 1

Slide 1 text

MIND READING - UNDERSTANDING RECOMMENDER SYSTEMS VLAD ILIESCU @

Slide 2

Slide 2 text

A VERY IMPORTANT QUESTION™

Slide 3

Slide 3 text

WHAT SUPER-POWER WOULD YOU LIKE?

Slide 4

Slide 4 text

MIND READING IS NICE THIS TIME OF YEAR

Slide 5

Slide 5 text

OFFLINE, IT’S PERSONAL

Slide 6

Slide 6 text

ONLINE, IT DOESN’T SCALE

Slide 7

Slide 7 text

ONLINE, IT DOESN’T SCALE UNLESS IT’S AUTOMATIC

Slide 8

Slide 8 text

EVERYBODY’S DOING IT SO WHY CAN’T WE?

Slide 9

Slide 9 text

REMEMBER NETFLIX’ 3-YEAR COMPETITION

Slide 10

Slide 10 text

WHAT ARE RECOMMENDER SYSTEMS ANYWAY?

Slide 11

Slide 11 text

THERE’S TWO TYPES OF RECOMMENDER SYSTEMS

Slide 12

Slide 12 text

CONTENT-BASED FILTERING 1.

Slide 13

Slide 13 text

COLLABORATIVE FILTERING 2.

Slide 14

Slide 14 text

OKAY, MAYBE THERE’S THREE

Slide 15

Slide 15 text

HYBRID SYSTEMS 3.

Slide 16

Slide 16 text

LET’S GO INTO A BIT MORE DETAIL

Slide 17

Slide 17 text

CONTENT-BASED FILTERING

Slide 18

Slide 18 text

- Gender - Age - Preferred genres - Artist - Year - Genre - Song Theme (extracted)

Slide 19

Slide 19 text

Song Alice Bob Carol Dave Genre Year The Weeknd - Starboy 3 5 Pop 2016 Luis Fonsi - Despacito 1 5 Dance 2017 Lorde - 400 Lux 1 2 4 5 Alternative, Pop 2013 Major Lazer - Light it Up 3 0 5 5 Dance 2016 The White Stripes - Seven Nation Army 4 1 2 1 Alternative 2003 Red Hot Chili Peppers - Scar Tissue 5 2 0 Alternative 2004 Taylor Swift - Shake it Off 3 5 2 Pop 2014

Slide 20

Slide 20 text

Song Carol Genre Year The Weeknd - Starboy Pop 2016 Luis Fonsi - Despacito 5 Dance 2017 Lorde - 400 Lux 4 Alternative, Pop 2013 Major Lazer - Light it Up 5 Dance 2016 The White Stripes - Seven Nation Army 2 Alternative 2003 Red Hot Chili Peppers - Scar Tissue 0 Alternative 2004 Taylor Swift - Shake it Off Pop 2014

Slide 21

Slide 21 text

Song Carol Alternative Dance Pop Year The Weeknd - Starboy 0 0 1 2016 Luis Fonsi - Despacito 5 0 1 0 2017 Lorde - 400 Lux 4 1 0 1 2013 Major Lazer - Light it Up 5 0 1 0 2016 The White Stripes - Seven Nation Army 2 1 0 0 2003 Red Hot Chili Peppers - Scar Tissue 0 1 0 0 2004 Taylor Swift - Shake it Off 0 0 1 2014

Slide 22

Slide 22 text

- DOESN’T DEPEND ON OTHER USERS - RECOMMEND UNPOPULAR ITEMS - COLD START ISSUES ARE LESS LIKELY advantages

Slide 23

Slide 23 text

- OVERSPECIALIZATION - DIFFICULTY EXTRACTING ATTRIBUTES FROM RICH MEDIA (IMAGES, AUDIO, MOVIES) disadvantages

Slide 24

Slide 24 text

COLLABORATIVE FILTERING

Slide 25

Slide 25 text

No content

Slide 26

Slide 26 text

- USER-USER - ITEM-ITEM - MATRIX FACTORIZATION approaches

Slide 27

Slide 27 text

Song Alice Bob Carol Dave The Weeknd - Starboy 3 5 Luis Fonsi - Despacito 1 5 Lorde - 400 Lux 1 2 4 5 Major Lazer - Light it Up 3 0 5 5 The White Stripes - Seven Nation Army 4 1 2 1 Red Hot Chili Peppers - Scar Tissue 5 2 0 Taylor Swift - Shake it Off 3 5 2

Slide 28

Slide 28 text

Slide 29

Slide 29 text

Slide 30

Slide 30 text

- DOESN’T NEED TO UNDERSTAND THE DATA advantages

Slide 31

Slide 31 text

- CANNOT RECOMMEND NEW ITEMS (THAT HAVEN’T BEEN RATED) - TENDS TO RECOMMEND POPULAR ITEMS disadvantages