or
or
By clicking below, you agree to our terms of service.
New to HackMD? Sign up
Syntax | Example | Reference | |
---|---|---|---|
# Header | Header | 基本排版 | |
- Unordered List |
|
||
1. Ordered List |
|
||
- [ ] Todo List |
|
||
> Blockquote | Blockquote |
||
**Bold font** | Bold font | ||
*Italics font* | Italics font | ||
~~Strikethrough~~ | |||
19^th^ | 19th | ||
H~2~O | H2O | ||
++Inserted text++ | Inserted text | ||
==Marked text== | Marked text | ||
[link text](https:// "title") | Link | ||
 | Image | ||
`Code` | Code |
在筆記中貼入程式碼 | |
```javascript var i = 0; ``` |
|
||
:smile: | ![]() |
Emoji list | |
{%youtube youtube_id %} | Externals | ||
$L^aT_eX$ | LaTeX | ||
:::info This is a alert area. ::: |
This is a alert area. |
On a scale of 0-10, how likely is it that you would recommend HackMD to your friends, family or business associates?
Please give us some advice and help us improve HackMD.
Syncing
xxxxxxxxxx
Scaling The E-Commerce Recommendations System - 黃耀慶(Arthur Huang)
歡迎來到 Hello World Dev Conf 共筆
共筆入口:https://hackmd.io/@HWDC/2024
Agenda
…
Challenges in LINE SHOPPING
Multi-Stage Recommmender
Retrieval
Two-Tower Model (雙塔模型)
User/Item Feature -> Model Tower -> Dot Product -> Product
In-Batch Negative Sampling
Feature Engineering
**Numeric Feature **
Categorical Feture
Text Feature
Feature Enineering
Retrieval - Inference
透過取得 Item/User Embedding,透過近似向量搜尋快速找到適合的推薦商品
Item (Offline)
User (Online)
Item2Item(猜你喜歡):以用戶喜歡的商品,與其他商品進行相似度比對
Ranking : Ranking based on user behavior in the module
雙塔模型無法使用user/item feature,所以會額外加上Ranking的手法
Deep Ranking Network
思考:為什麼不能拿有曝光,但沒點擊的項目作為Negative?
透過 PySpark 進行 scaling
Re-rank: Ranking by Divefrsity, Freshness, Business Logic
Diversity (推薦多樣性)
Freshness (保持用戶的新鮮程度,新商品上架沒資料的時候可以這樣推)
Business Logic (特定節慶/檔期)
推薦系統本質上是一個GMV(網站成交金额)放大器
Model Training - Petastorm
ML flow
Pytorch Lighting
Airflow
聊天區
好難記…都是圖
看講者能不能提供投影片了, .