Features - DATA MINING CUP - 2022

You might also like

Download as pdf or txt
Download as pdf or txt
You are on page 1of 2

DATA MINING CUP 2022

items.csv
Column name Description Value Range / Format

Unique identifier for every Positive Integer


itemID
product [0, …, 32775]

Integer*
brand Brand of the product
[-1, …, 1513]

Descriptive feature Integer*


feature_1
(categorical) [-1, …, 10]

Descriptive feature Positive Integer


feature_2
(categorical) {0, 1, 2, 3}

Descriptive feature Integer*


feature_3
(categorical) [-1, …, 538]

Descriptive feature Integer*


feature_4
(categorical) {-1, 0, 1, 2, 3, 4}

Descriptive feature Integer*


feature_5
(categorical) [-1, …, 190]

Comma-separated list of
categories List of associated categories
integers

* The value of –1 corresponds to no feature value.

category_hierarchy.csv
Column name Description Value Range / Format

Positive Integer
category Category identifier
[0, …, 4299]
Broader (parent) category Positive Integer
parent_category associated with a category subset of the integer range of
identifier the column ‘category’
orders.csv
Column name Description Value Range / Format

YYYY-MM-dd
date Date of the transaction from 2020-06-01
to 2021-01-31

Positive Integer
userID Unique identifier for users
[0, …, 46137]

Positive Integer
itemID Item identifier of the sold item
[0, …, 32775]

Number of orders of a product


order at a given date by a specific Positive Integer
user

submission.csv
Column name Description Value Range / Format

Positive Integer,
userID Unique identifier for users subset of the userIDs in
orders.csv
Positive Integer,
itemID Item identifier of the sold item subset of the itemIDs in
items.csv

Column to be filled by the Positive Integer


prediction
participating teams {0, 1, 2, 3, 4}

You might also like