預測模型專案 進到職場後: DS DE MLE DA PM Biz DS DE DS DS DE DA MLE EDA Model build Hyper- parameter tuning Evaluation Feature Engineering Error analysis Data preparation Scaling Performance Model decay Data drift ?
預測模型專案 進到職場後: DS DE MLE DA PM Biz DS DE DS DS DE DA MLE EDA Model build Hyper- parameter tuning Evaluation Feature Engineering Error analysis Data preparation Scaling Performance Model decay Data drift ? Biz problem ML problem Key metrics How to use ⾊情貼⽂辨識 檢舉率 / 曝光量 定期偵測排除 Method 影像辨識 / 社群網絡 找出⾊情貼⽂
預測模型專案 進到職場後: DS DE MLE DA PM Biz DS DE DS DS DE DA MLE EDA Model build Hyper- parameter tuning Evaluation Feature Engineering Error analysis Data preparation Scaling Performance Model decay Data drift ? 潛在問題: • 資料散落各地，形同孤島 • 權限控管 • 指標定義不同 • ⽂件沒有統⼀格式
預測模型專案 進到職場後: DS DE MLE DA PM Biz DS DE DS DS DE DA MLE EDA Model build Hyper- parameter tuning Evaluation Feature Engineering Error analysis Data preparation Scaling Performance Model decay Data drift 1. 將 [統計指標] 轉換成 [商業指標] 2. 線下與線上測試 ?
預測模型專案 進到職場後: DS DE MLE DA PM Biz DS DE DS DS DE DA MLE EDA Model build Hyper- parameter tuning Evaluation Feature Engineering Error analysis Data preparation Scaling Performance Model decay Data drift 批量預測 或 即時預測 ?
預測模型專案 進到職場後: DS DE MLE DA PM Biz DS DE DS DS DE DA MLE EDA Model build Hyper- parameter tuning Evaluation Feature Engineering Error analysis Data preparation Scaling Performance Model decay Data drift ?
Data Dev LINE Family Services LINE SHOPPING LINE SPOT LINE MUSIC LINE Sticker LINE VOOM LINE Reward Fact Checker LINE HELP TW LINE Travel NLP Knowledge Graph Uplift Modeling NER Classifier Duplication Detector Auto completion Keyword Extraction Related Search Text Generation User Tagging Data Analytics Recom- mendation CLV LINE TODAY ⽽Data Dev Team，就是在思考如何跨服務強化數據賦能
line_developers_tw
hygradme
tkikuchi1002
bigwheel
mosa_siru
orgachem
mtx2s
etaroid
takesection
onlinesalon
leveragestech
tyrmanuz
toshi0383
3n
kneath
jlugia
mza
addyosmani
productmarketing
tammyeverts
mraible
lara
reverentgeek
geoffreycrofte
speakerdeck