Slide 1

Slide 1 text

No content

Slide 2

Slide 2 text

Self Introduction › Joined LINE Corporation as a Data Scientist in May 2019 › Working on data analysis for LINE Sticker Service › Naho Tanigawa

Slide 3

Slide 3 text

Agenda › Sticker Keyboard Project › Challenging Task 1 : Definition of Session › Challenging Task 2 : Identification of KPI › Case Studies of Analysis

Slide 4

Slide 4 text

Sticker Keyboard Project < Goal > Increase the frequency of sending stickers < Approach > Reduce time to search and send stickers Sticker Sticker Keyboard

Slide 5

Slide 5 text

Data-Driven Improvement User Activity logs Analysis Collecting Data feedback

Slide 6

Slide 6 text

Data-Driven Improvement User Activity logs Analysis Collecting Data feedback We have no data of sent contents nor user identity.

Slide 7

Slide 7 text

Sticker Keyboard Update new functions released in June 2020

Slide 8

Slide 8 text

Sticker Keyboard Update new functions released in June 2020 New panel for searching stickers Notification of time-limited sticker’s expiration

Slide 9

Slide 9 text

2 Challenging Tasks Definition of Session Identification of KPI

Slide 10

Slide 10 text

Definition of Session

Slide 11

Slide 11 text

Problem Logs of 1 LINE App. Launch = sending stickers E Need to group sequences for understanding user behavior 1 LINE App launch: Too long 1 action on Sticker keyboard: Too short

Slide 12

Slide 12 text

1 Session on sending a sticker Problem Logs of 1 LINE App. Launch = sending stickers E E 1st session 2nd session 3rd session E E Need to group sequences for understanding user behavior 1 LINE App launch: Too long 1 action on Sticker keyboard: Too short

Slide 13

Slide 13 text

Solution Define session by splitting log based on rules S Action to start session Action to end session (Sending stickers) E Click E S 1st session 2nd session 3rd session Logs of 1 LINE App. Launch E S Click We have no data of sent contents nor user identity.

Slide 14

Slide 14 text

Solution User Activity logs Randomly sample the logs of 1% of all users Splitting logs by rule-based Estimated Statistics By × 100 Action to start session Action to end session (sending stickers) E Pipeline of processing session logs Session Logs S 1st session 2nd session 3rd session Logs of 1 LINE App. Launch E E S S 10 billion in a day

Slide 15

Slide 15 text

Identification of KPI

Slide 16

Slide 16 text

Problem Identify KPI to represent both Goal & Approach < Goal > Increase the frequency of sending stickers < Approach > Reduce time to search and send stickers

Slide 17

Slide 17 text

Solution # of Sending Sticker Count # of Unique Sending Users Average Sending Sticker Count per Users Goal

Slide 18

Slide 18 text

Solution # of Sending Sticker Count # of Unique Sending Users Average Sending Sticker Count per Users Average Sending Sticker Count in 1 App Launch per Users Average App Launch Count per Users Goal

Slide 19

Slide 19 text

Solution Sending Sticker Count in 1 App Launch per Users 2 # of Sending Sticker Count = sending stickers E # of Unique Sending Users Average Sending Sticker Count per Users Average Sending Sticker Count in 1 App Launch per Users Average App Launch Count per Users Goal Approach E S 1st session 2nd session 3rd session Logs of 1 LINE App. Launch E S

Slide 20

Slide 20 text

Solution ≒ Elapsed Time of 1 App Launch Elapsed Time of Sending 1 sticker Sending Sticker Count in 1 App Launch per Users 2 # of Sending Sticker Count = sending stickers E # of Unique Sending Users Average Sending Sticker Count per Users Average Sending Sticker Count in 1 App Launch per Users Average App Launch Count per Users Goal Approach E S 1st session 2nd session 3rd session Logs of 1 LINE App. Launch E S

Slide 21

Slide 21 text

Case Studies of Analysis

Slide 22

Slide 22 text

Case 1 : UI of New sticker panel Reduce time to send stickers by allowing users to do the most common way TO-BE Input method in new sticker panel: double-click a sticker … AS-IS Most frequent sending pattern: double-click a sticker 26%

Slide 23

Slide 23 text

Case 2 : Notification Timing of time- limited sticker’s expiration expiration Download date Reduce time to search stickers by highlighting stickers near expiration AS-IS Last use date of time-limited stickers: Increase in 10 days before expiration TO-BE Notification timing: 10 days before expiration

Slide 24

Slide 24 text

Data-Driven Improvement User Activity logs Analysis Collecting Data feedback

Slide 25

Slide 25 text

Thank you