rel-amazon Amazon e-commerce database
Database Description: The Amazon e-commerce relational database is a product and user purchasing behavior across Amazon's e-commerce platform. Notably, it contains rich information about each product and transactions. The product table includes price and category information; the review table includes overall rating, whether the user has actually bought the product, and the text of the review itself. We use the subset of book-related products.
Database Statistics:
| Domain | E-Commerce |
| Num of Tables | 3 |
| Num of Rows | 24,291,489 |
| Num of Columns | 15 |
| Starting time | 1996-06-25 |
| Validation timestamp | 2015-01-01 |
| Testing timestamp | 2016-01-01 |
| Time window size | 3 months |
Database schema:
To load this relational database in RelBench, do:
from relbench.datasets import get_dataset
dataset = get_dataset("rel-amazon")
References:
Dataset License: Not specified.
Node Classification Tasks
user-churn
Task Description: For each user, predict 1 if the customer does not review any product in the next 3 months, and 0 otherwise.
Evaluation metricAUROC
from relbench.datasets import get_dataset
dataset = get_dataset("rel-amazon")
task = dataset.get_task("user-churn")
task.train_table, task.val_table, task.test_table # training/validation/testing tables
item-churn
Task Description: For each product, predict 1 if the product does not receive any reviews in the next 3 months.
Evaluation metricAUROC
from relbench.datasets import get_dataset
dataset = get_dataset("rel-amazon")
task = dataset.get_task("item-churn")
task.train_table, task.val_table, task.test_table # training/validation/testing tables
Node Regression Tasks
user-ltv
Task Description: For each user, predict the $ value of the total number of products they buy and review in the next 3 months.
Evaluation metricMAE
To load the dataset and the split, do:
from relbench.datasets import get_dataset
dataset = get_dataset("rel-amazon")
task = dataset.get_task("user-ltv")
task.train_table, task.val_table, task.test_table # training/validation/testing tables
item-ltv
Task Description: For each product, predict the $ value of the total number purchases and reviews it recieves in the next 3 months.
Evaluation metricMAE
To load the dataset and the split, do:
from relbench.datasets import get_dataset
dataset = get_dataset("rel-amazon")
task = dataset.get_task("user-ltv")
task.train_table, task.val_table, task.test_table # training/validation/testing tables
Link Prediction Tasks
user-item-purchase
Task Description: Predict the list of distinct items each customer will pur- chase in the next 3 months.
Evaluation metricMAP
To load the dataset and the split, do:
from relbench.datasets import get_dataset
dataset = get_dataset("rel-amazon")
task = dataset.get_task("user-item-purchase")
task.train_table, task.val_table, task.test_table # training/validation/testing tables
user-item-rate
Task Description: Predict the list of distinct items each customer will purchase and give a 5 star review in the next 3 months.
Evaluation metricMAP
To load the dataset and the split, do:
from relbench.datasets import get_dataset
dataset = get_dataset("rel-amazon")
task = dataset.get_task("user-item-rate")
task.train_table, task.val_table, task.test_table # training/validation/testing tables
user-item-review
Task Description: Predict the list of distinct items each customer will purchase and give a detailed review in the next 3 months.
Evaluation metricMAP
To load the dataset and the split, do:
from relbench.datasets import get_dataset
dataset = get_dataset("rel-amazon")
task = dataset.get_task("user-item-review")
task.train_table, task.val_table, task.test_table # training/validation/testing tables