coop_purchases — Coop supermarket purchases (2007-2011)

Description

A bipartite network of the customers of the Italian retail company Coop and the products they bought, released by D. Pennacchioli, M. Coscia, S. Rinzivillo, D. Pedreschi and F. Giannotti as the companion data set of their study of the "product range effect". The data cover the purchases recorded between January 2007 and December 2011 by 60,365 anonymized customers (holders of a loyalty card) in five shops of the company, and 4,567 products. Nodes are customers and products, and an edge connects a customer to a product they bought in a given shop, with quantity equal to the total number of items of the product bought by the customer in that shop over the whole period. A customer and a product are thus connected by up to five parallel edges, one for each shop.

The network has the following properties:

is_customer: whether the node is a customer (otherwise it is a product).
id: the identifier of the customer or of the product in the source data.
price (products): the unit price of the product in euros, averaged over the time span of the data set.
shop_distance (customers): the distances, in metres, from the customer's home to each of the five shops (shop identifiers 1 to 5, in this order), measured as straight lines, not along the road network.
shop (edges): the identifier of the shop (1 to 5) where the purchases were made.
quantity (edges): the number of items bought.

The customer with identifier 44,617 (in the range from 1 to 60,366) has no purchases in the data, and is included as an isolated node.

Tags

Economic Commerce Weighted Multigraph Metadata

Citation

D. Pennacchioli, M. Coscia, S. Rinzivillo, D. Pedreschi, F. Giannotti, "Explaining the product range effect in purchase data." 2013 IEEE International Conference on Big Data, 648-656 (2013) 10.1109/BigData.2013.6691634 Sci-Hub

Upstream URL OK

https://www.michelecoscia.com/?page_id=379

Networks

Tip: hover over a column header for a description.

Column legend

$\left<k\right>$: Mean degree
$\sigma_k$: Standard deviation of the degrees
$\lambda_h$: Largest eigenvalue of the Hashimoto (non-backtracking) matrix
$\tau$: Random walk mixing time
$r$: Degree assortativity
$c$: Global clustering coefficient
$\oslash$: (Pseudo-) diameter
$S$: Relative size of the largest component
NPs: Node properties
EPs: Edge properties

Name	Nodes	Edges	$\left<k\right>$	$\sigma_k$	$\lambda_h$	$\tau$	$r$	$c$	$\oslash$	$S$	Kind	Mode	NPs	EPs	gt	GraphML	GML	csv
coop_purchases	64,933	24,638,725	758.90	2980.03	2776.38	0.77	-0.46	0.00	6	1.00	Undirected	Bipartite	is_customer id price shop_distance	shop quantity	29.2 MiB	92.1 MiB	93.8 MiB	75.3 MiB