東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Developing a Recommender System for ...

Powell, Laurel Boykin.

FindBook

Google Book

Amazon

博客來

Developing a Recommender System for Pricing Contemporary Fine Art.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Developing a Recommender System for Pricing Contemporary Fine Art./
作者:	Powell, Laurel Boykin.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
面頁冊數:	301 p.
附註:	Source: Dissertations Abstracts International, Volume: 82-03, Section: B.
Contained By:	Dissertations Abstracts International82-03B.
標題:	Computer science. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28086718
ISBN:	9798664710908

Developing a Recommender System for Pricing Contemporary Fine Art.
Powell, Laurel Boykin.

Developing a Recommender System for Pricing Contemporary Fine Art. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 301 p.

Source: Dissertations Abstracts International, Volume: 82-03, Section: B.

Thesis (Ph.D.)--The University of North Carolina at Charlotte, 2020.

This item must not be sold to any third party vendors.

The art market is a large and growing part of the global economy. However, uncertainty about prices, which can be problematic for many shareholders, can inhibit the growth of this market. This work discusses methods for the development of a knowledge based recommender system that will price contemporary fine art. Artworks are unique and often rare purchases. This makes a knowledge based system particularly suitable for that problem area. To the knowledge of this researcher, there are no knowledge based recommender systems for artwork pricing currently available.In this dissertation, I will discuss past research in the field of art analytics, and the competing factors which drive art prices. I will also discuss the dataset that has been collected for use on this project. I will then discuss the development of both visual and textual features for this recommender system. Methods for the clustering of artists using visual features will be discussed. This work will also include an exploration of the development of personalized models based on these artist clusters and discuss their impact on the efficacy of the models built.Lastly, this work will discuss a final structure for a recommender system and how it could be created moving forward.

ISBN: 9798664710908Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Action Rules

Developing a Recommender System for Pricing Contemporary Fine Art.
LDR:02430nmm a2200373 4500 001 2280065
005 20210823091509.5
008 220723s2020 ||||||||||||||||| ||eng d
020 $a 9798664710908
035 $a (MiAaPQ)AAI28086718
035 $a AAI28086718
040 $a MiAaPQ $c MiAaPQ
100 1 $a Powell, Laurel Boykin. $3 3558566
245 1 0 $a Developing a Recommender System for Pricing Contemporary Fine Art.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 301 p.
500 $a Source: Dissertations Abstracts International, Volume: 82-03, Section: B.
500 $a Advisor: Ras, Zbigniew W.
502 $a Thesis (Ph.D.)--The University of North Carolina at Charlotte, 2020.
506 $a This item must not be sold to any third party vendors.
520 $a The art market is a large and growing part of the global economy. However, uncertainty about prices, which can be problematic for many shareholders, can inhibit the growth of this market. This work discusses methods for the development of a knowledge based recommender system that will price contemporary fine art. Artworks are unique and often rare purchases. This makes a knowledge based system particularly suitable for that problem area. To the knowledge of this researcher, there are no knowledge based recommender systems for artwork pricing currently available.In this dissertation, I will discuss past research in the field of art analytics, and the competing factors which drive art prices. I will also discuss the dataset that has been collected for use on this project. I will then discuss the development of both visual and textual features for this recommender system. Methods for the clustering of artists using visual features will be discussed. This work will also include an exploration of the development of personalized models based on these artist clusters and discuss their impact on the efficacy of the models built.Lastly, this work will discuss a final structure for a recommender system and how it could be created moving forward.
590 $a School code: 0694.
650 4 $a Computer science. $3 523869
650 4 $a Fine arts. $3 2122690
650 4 $a Information technology. $3 532993
653 $a Action Rules
653 $a Art Analytics
653 $a Data Mining
653 $a Knowledge Based Systems
653 $a Recommender Systems
690 $a 0984
690 $a 0489
690 $a 0357
710 2 $a The University of North Carolina at Charlotte. $b Computer Science. $3 3181506
773 0 $t Dissertations Abstracts International $g 82-03B.
790 $a 0694
791 $a Ph.D.
792 $a 2020
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28086718