Hierarchical Sales Data

Donated on 7/2/2021

This dataset contains hierarchical sales data gathered from an Italian grocery store

Dataset Characteristics

Time-Series

Subject Area

Engineering

Associated Tasks

Clustering, Other

Feature Type

-

# Instances

1798

# Features

237

Dataset Information

Additional Information

The dataset consists of 118 daily time series representing the SKU-level sales from 01/01/2014 to 31/12/2018 of 4 national pasta brands. Besides univariate time series data, the quantity sold is integrated by information on the presence or the absence of a promotion. These time series can be naturally arranged to follow a 3-level hierarchical structure (see https://www.sciencedirect.com/science/article/pii/S0957417421005431). - QTY_B'X'_'Y' - the quantity sold for brand 'X' item 'Y' - PROMO_B'X'_'Y' - the promotion flag for brand 'X' and item 'Y'

Has Missing Values?

No

Introductory Paper

A machine learning approach for forecasting hierarchical time series

By Paolo Mancuso, Veronica Piccialli, Antonio M. Sudoso. 2021

Published in Journal

Variables Table

Variable NameRoleTypeDescriptionUnitsMissing Values
QTY_B2_3FeatureIntegerno
QTY_B2_4FeatureIntegerno
QTY_B2_5FeatureIntegerno
QTY_B2_6FeatureIntegerno
QTY_B2_7FeatureIntegerno
QTY_B2_8FeatureIntegerno
QTY_B2_9FeatureIntegerno
QTY_B2_10FeatureIntegerno
QTY_B2_11FeatureIntegerno
QTY_B2_12FeatureIntegerno

0 to 10 of 237

Reviews

There are no reviews for this dataset yet.

Login to Write a Review
Download
1 citations
14339 views

Keywords

hierarchical time seriesforecast

Creators

Paolo Mancuso

paolo.mancuso@uniroma2.it

University of Rome Tor Vergata

Veronica Piccialli

veronica.piccialli@uniroma2.it

University of Rome Tor Vergata

Antonio M. Sudoso

antonio.maria.sudoso@uniroma2.it

University of Rome Tor Vergata

Notes

License

By using the UCI Machine Learning Repository, you acknowledge and accept the cookies and privacy practices used by the UCI Machine Learning Repository.

Read Policy