Home > Data Lab > Data Set
  • Ali_Mum_Baby

    Providers : Taobao & Tmall

    Posted : 2015.05.28

    #Participants : 680

Data Set Description

Document (You can download after you login)

Format

(sample)sam_tianchi_mum_baby.csv

.csv (20KB)

(sample)sam_tianchi_mum_baby_trade_history.csv

.csv (8MB)


Introduction

Ali_Mum_Baby is a dataset that contains more than 9 million children's info (birthday and gender) provided by consumers who share the information in order to receive better recommendations or search results.

Tianchi_mum_baby
It contains more than 9,000,000 children's birthday and gender provided by consumers in Taobao or Tmall.

Column 

Description 

user_id 

User ID (Bigint). 

birthday 

Children's birthday (e.g. 20130423). 

gender 

Children's gender ("0" denotes female, "1" denotes male, "2" denotes unknown). 


Tianchi_mum_baby_trade_history
The table contains historical trade info of Taobao members.

Column 

Description 

item_id 

Item ID (Bigint). 

user_id 

User ID (Bigint). 

cat_id 

Category ID (Bigint). 

cat1 

Root category ID (Bigint). 

property 

Property of the corresponding item (String). 

buy_mount 

Purchase quantity (Bigint). 

day 

Timestamp. 


Typical research topics
Predict children's ages based on their parents' purchase behavior, or predict what kind of goods a user would buy based on their children's info (age, gender etc.)
 
Reference and Related Publications
Peng Jiang, Yadong Zhu, Yi Zhang, Quan Yuan, Life-stage Prediction for Product Recommendation in E-commerce. To appear in Proceedings of the 21th ACM SIGKDD international conference on Knowledge discovery and data mining, ACM, 2015.