Visualizable and explicable recommendations obtained from price estimation functions

Claudia Becerra; Fabio Gonzalez; Alexander Gelbukh

Visualizable and explicable recommendations obtained from price estimation functions

Claudia Becerra, Fabio Gonzalez, Alexander Gelbukh

Centro de Investigación en Computación (CIC)

Research output: Contribution to journal › Conference article › peer-review

5 Scopus citations

Abstract

Collaborative filtering is one of the most common approaches in many current recommender systems. However, historical data and customer profiles, necessary for this approach, are not always available. Similarly, new products are constantly launched to the market lacking historical information. We propose a new method to deal with these "cold start" scenarios, designing price-estimation functions used for making recommendations based on cost-benefit analysis. Experimental results, using a data set of 836 laptop descriptions, showed that such price-estimation functions can be learned from data. Besides, they can also be used to formulate interpretable recommendations that explain to users how product features determine its price. Finally a 2D visualization of the proposed recommender system was provided.

Original language	English
Pages (from-to)	27-34
Number of pages	8
Journal	CEUR Workshop Proceedings
Volume	811
State	Published - 2011
Event	Joint Workshop on Human Decision Making in Recommender Systems, Decisions@RecSys 2011 and User-Centric Evaluation of Recommender Systems and Their Interfaces-2, UCERSTI 2 - Affiliated with the 5th ACM Conference on Recommender Systems, RecSys 2011 - Chicago, IL, United States Duration: 23 Oct 2011 → 26 Oct 2011

Keywords

Apriori recommendation
Cold-start recommendation
Price estimation functions

Cite this

@article{f273ccec3f474dd59d682bedc8c36959,

title = "Visualizable and explicable recommendations obtained from price estimation functions",

abstract = "Collaborative filtering is one of the most common approaches in many current recommender systems. However, historical data and customer profiles, necessary for this approach, are not always available. Similarly, new products are constantly launched to the market lacking historical information. We propose a new method to deal with these {"}cold start{"} scenarios, designing price-estimation functions used for making recommendations based on cost-benefit analysis. Experimental results, using a data set of 836 laptop descriptions, showed that such price-estimation functions can be learned from data. Besides, they can also be used to formulate interpretable recommendations that explain to users how product features determine its price. Finally a 2D visualization of the proposed recommender system was provided.",

keywords = "Apriori recommendation, Cold-start recommendation, Price estimation functions",

author = "Claudia Becerra and Fabio Gonzalez and Alexander Gelbukh",

year = "2011",

language = "Ingl{\'e}s",

volume = "811",

pages = "27--34",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

publisher = "CEUR-WS",

note = "Joint Workshop on Human Decision Making in Recommender Systems, Decisions@RecSys 2011 and User-Centric Evaluation of Recommender Systems and Their Interfaces-2, UCERSTI 2 - Affiliated with the 5th ACM Conference on Recommender Systems, RecSys 2011 ; Conference date: 23-10-2011 Through 26-10-2011",

}

TY - JOUR

T1 - Visualizable and explicable recommendations obtained from price estimation functions

AU - Becerra, Claudia

AU - Gonzalez, Fabio

AU - Gelbukh, Alexander

PY - 2011

Y1 - 2011

N2 - Collaborative filtering is one of the most common approaches in many current recommender systems. However, historical data and customer profiles, necessary for this approach, are not always available. Similarly, new products are constantly launched to the market lacking historical information. We propose a new method to deal with these "cold start" scenarios, designing price-estimation functions used for making recommendations based on cost-benefit analysis. Experimental results, using a data set of 836 laptop descriptions, showed that such price-estimation functions can be learned from data. Besides, they can also be used to formulate interpretable recommendations that explain to users how product features determine its price. Finally a 2D visualization of the proposed recommender system was provided.

AB - Collaborative filtering is one of the most common approaches in many current recommender systems. However, historical data and customer profiles, necessary for this approach, are not always available. Similarly, new products are constantly launched to the market lacking historical information. We propose a new method to deal with these "cold start" scenarios, designing price-estimation functions used for making recommendations based on cost-benefit analysis. Experimental results, using a data set of 836 laptop descriptions, showed that such price-estimation functions can be learned from data. Besides, they can also be used to formulate interpretable recommendations that explain to users how product features determine its price. Finally a 2D visualization of the proposed recommender system was provided.

KW - Apriori recommendation

KW - Cold-start recommendation

KW - Price estimation functions

UR - http://www.scopus.com/inward/record.url?scp=84891906323&partnerID=8YFLogxK

M3 - Artículo de la conferencia

AN - SCOPUS:84891906323

SN - 1613-0073

VL - 811

SP - 27

EP - 34

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

T2 - Joint Workshop on Human Decision Making in Recommender Systems, Decisions@RecSys 2011 and User-Centric Evaluation of Recommender Systems and Their Interfaces-2, UCERSTI 2 - Affiliated with the 5th ACM Conference on Recommender Systems, RecSys 2011

Y2 - 23 October 2011 through 26 October 2011

ER -

Visualizable and explicable recommendations obtained from price estimation functions

Abstract

Keywords

Other files and links

Fingerprint

Cite this