Description of Dataset used in Fetchback® Competition

File Name: DataForClass.txt

File Size: ~786MB

Number of Tuples: 13,584,386

Number of Attributes in the Table: 4

The data is gathered by Fetchback® (www.fetchback.com), a retargeting company, for research use. It consists of the transaction records in one week (08/08/2010 – 08/14/2010).

In this dataset, each row represents a transaction, which has 4 attributes, namely pid, siteid, uid and date.

· pid is the unique identifier for each product, varying from 7 to 8 digits.

· siteid is the unique identifier for each online shopping website, 4 digits.

· uid is the unique identifier for each user, varying from 3 to 8 digits.

· date is the transaction date.

Sample tuples of the data:

pid:13505646 - siteId:9093 - uid:08097540 - date:2010-08-08

pid:16062417 - siteId:9102 - uid:95429188 - date:2010-08-08

pid:12546546 - siteId:7167 - uid:71516943 - date:2010-08-08

pid:691224 - siteId:4266 - uid:07079557 - date:2010-08-08

pid:4577421 - siteId:4266 - uid:07079557 - date:2010-08-08