Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Feature as a Service at Data Labs

Feature as a Service at Data Labs

Chaerim Yeo
LINE Machine Learning Team Senior Software Engineer
https://linedevday.linecorp.com/jp/2019/sessions/C1-5

LINE DevDay 2019

November 20, 2019
Tweet

More Decks by LINE DevDay 2019

Other Decks in Technology

Transcript

  1. 2019 DevDay Feature as a Service at Data Labs >

    Chaerim Yeo > LINE Machine Learning Team Senior Software Engineer
  2. DATA LABS Sticker Data Labs Ad Manga Music Live News

    > Independent from service/dev depts. > Aggregate data across various services > Provide analysis/solution from data across various services
  3. > Collection of users' behavioral logs across various LINE services

    Z-FEATURES OVERVIEW Transform into structures 
 that cover about 80% of 
 all ML use cases
  4. > Collection of users' behavioral logs across various LINE services

    Z-FEATURES OVERVIEW {...} {...} {...} {...} {...} {...} ... ...
  5. > Obfuscated user features > Mitigate z-features' problems • Accumulate

    content embedding based on users' behavioral logs • Reduce dimensionality Y-FEATURES OVERVIEW
  6. > Obfuscated user features > Mitigate z-features' problems • Accumulate

    content embedding based on users' behavioral logs • Reduce dimensionality Y-FEATURES OVERVIEW
  7. > Obfuscated user features > Mitigate z-features' problems • Accumulate

    content embedding based on users' behavioral logs • Reduce dimensionality Y-FEATURES OVERVIEW
  8. > Obfuscated user features > Mitigate z-features' problems • Accumulate

    content embedding based on users' behavioral logs • Reduce dimensionality Y-FEATURES OVERVIEW Matrix sketching + PCA
  9. Y-FEATURES USER DEMOGRAPHICS ESTIMATION FOR JP REGION GENDER ESTIMATION METRICS


    (RELATIVE TO Z-FEATURES) 0 0.25 0.5 0.75 1 precision recall f1-score 1.00 1.00 0.99 AGE-GROUP ESTIMATION METRICS
 (RELATIVE TO Z-FEATURES) 0 0.25 0.5 0.75 1 precision recall f1-score 0.88 0.88 0.88 REGION ESTIMATION METRICS
 (RELATIVE TO Z-FEATURES) 0 0.25 0.5 0.75 1 precision recall f1-score 0.98 0.98 0.99
  10. Y-FEATURES USER DEMOGRAPHICS ESTIMATION FOR JP REGION TRAINING TIME
 (RELATIVE

    TO Z-FEATURES) 0 0.25 0.5 0.75 1 gender age-group region 0.06 0.02 0.05 PREDICTION TIME
 (RELATIVE TO Z-FEATURES) 0 0.25 0.5 0.75 1 gender age-group region 0.52 0.51 0.20
  11. C-FEATURES OVERVIEW > Embedding of each service's contents > Currently

    available for two services • News articles: SCDV with fastText • Sticker images: Xception
  12. HOW WE USE FEATURES AT DATA LABS > Feature as

    a Service • Achieve data standardization/democratization • Improve development efficiency > Available Features • User features • Obfuscated user features • Content features