Center for Machine Learning and Intelligent Systems
About  Citation Policy  Donate a Data Set  Contact


Repository Web            Google
View ALL Data Sets

PANDOR Data Set
Download: Data Folder, Data Set Description

Abstract: PANDOR is a novel and publicly available dataset for online recommendation provided by Purch ([Web Link]).

Data Set Characteristics:  

Multivariate

Number of Instances:

N/A

Area:

Life

Attribute Characteristics:

Categorical

Number of Attributes:

N/A

Date Donated

2018-10-02

Associated Tasks:

Recommendation

Missing Values?

N/A

Number of Web Hits:

3762


Source:

Massih-Reza Amini
Univ. Grenoble Alpes, CNRS/LIG
massih-reza.amini '@' univ-grenoble-alpes.fr

Charlotte Laclau
Univ. Grenoble Alpes, CNRS/LIG
charlotte.laclau '@' univ-grenoble-alpes.fr

Sumit Sidana
Univ. Grenoble Alpes, CNRS/LIG
sumit.sidana '@' imag.fr


Data Set Information:

source, offerId, pageViewId, offerViewId, utcDate, keywords, wasClicked, offerViewCountPerPageView, clickCountPerPageView, userId, productLemmas, productFeatures, url, pageLemmas, pageFeatures

# Events: 48,602,664
# Users: 5,894,431
# Offers: 14,716
# Clicks: 337,511
# OffersShown: 48,754,927
# Max offers shown to 1 user: 2,029
# Max clicks done by 1 user: 119

Average # Offers Shown to 1 user: 8.271
Average # Clicks done by 1 user: 0.057
Average # Clicks done by 1 user (if user did at least 1 click): 1.350616661464461


# Events where user did at least 1 click: 4,544,848
# Events which have at least 1 page text words: 1,212,170
# Events which have at least 1 product Text words: 450,050
# Events which have at least 1 keyword: 4,492,544

page text vocabulary size: 9,111
product text vocabulary size: 6,016
keyword vocabulary size: 543


Out of 9,847 offers, 2,701 offers have at least 1 text word (27.4%)
Out of 7,092 pages, 1,990 pages have at least 1 text word (28.1%)



Attribute Information:

Provide information about each attribute in your data set.


Relevant Papers:

Sumit Sidana, Charlotte Laclau, Massih-Reza Amini. 'Learning to Recommend Diverse Items over Implicit Feedback on PANDOR', RecSYS 2018.



Citation Request:

If you publish results based on this data set, please acknowledge its use, by referring to:
Sumit Sidana, Charlotte Laclau, Massih-Reza Amini. 'Learning to Recommend Diverse Items over Implicit Feedback on PANDOR', RecSYS 2018.


Supported By:

 In Collaboration With:

About  ||  Citation Policy  ||  Donation Policy  ||  Contact  ||  CML