| LDR | | 02825nmm uu200433 4500 |
| 001 | | 000000333632 |
| 005 | | 20240805173414 |
| 008 | | 181129s2018 |||||||||||||||||c||eng d |
| 020 | |
▼a 9780438289369 |
| 035 | |
▼a (MiAaPQ)AAI10749654 |
| 035 | |
▼a (MiAaPQ)ucdavis:17749 |
| 040 | |
▼a MiAaPQ
▼c MiAaPQ
▼d 248032 |
| 082 | 0 |
▼a 004 |
| 100 | 1 |
▼a Goswami, Anjan. |
| 245 | 10 |
▼a Machine-Learned Ranking Algorithms for E-commerce Search and Recommendation Applications. |
| 260 | |
▼a [S.l.] :
▼b University of California, Davis.,
▼c 2018 |
| 260 | 1 |
▼a Ann Arbor :
▼b ProQuest Dissertations & Theses,
▼c 2018 |
| 300 | |
▼a 188 p. |
| 500 | |
▼a Source: Dissertation Abstracts International, Volume: 79-12(E), Section: B. |
| 500 | |
▼a Advisers: Prasant Mohapatra |
| 502 | 1 |
▼a Thesis (Ph.D.)--University of California, Davis, 2018. |
| 520 | |
▼a Search is one of the most critical functionalities of an e-commerce site. Almost every e-commerce site provides a search box. A customer expresses her intent about a product or a category of products in the form of one or more keywords and enter |
| 520 | |
▼a We begin with the aspect of the evaluation of the ranking algorithms for an e-commerce search and provide guidelines for conducting online randomized controlled experiments on a large e-commerce site. In this regard, we discuss managing biases, |
| 520 | |
▼a Second, we define a formal framework for designing learning to rank (LTR) algorithms for e-commerce search optimizing the ranking for relevance, revenue, and discovery. We define a measure for discovery and describe the importance of that for an |
| 520 | |
▼a Third, we address the problem of incorporating diversity in e-commerce search. We design a knapsack based semi-bandit optimization algorithm for simultaneously learning to diversify and maximizing the revenue. We show that the regret of the algo |
| 520 | |
▼a Fourth, we address the problem of multi-objective learning to rank. We use the LambdaMart algorithm to realize our multi-objective algorithms. LambdaMart algorithm is widely used in Industry, won some recent "learning to rank" challenges. The au |
| 520 | |
▼a Fifth, we address the problem of quantification and visualization of the excess supply and unmet demand using the contents of the queries and items. We show the impact of such content gap in search experience. We quantify the content gap definin |
| 590 | |
▼a School code: 0029. |
| 650 | 4 |
▼a Computer science. |
| 690 | |
▼a 0984 |
| 710 | 20 |
▼a University of California, Davis.
▼b Computer Science. |
| 773 | 0 |
▼t Dissertation Abstracts International
▼g 79-12B(E). |
| 773 | |
▼t Dissertation Abstract International |
| 790 | |
▼a 0029 |
| 791 | |
▼a Ph.D. |
| 792 | |
▼a 2018 |
| 793 | |
▼a English |
| 856 | 40 |
▼u http://www.riss.kr/pdu/ddodLink.do?id=T14997054
▼n KERIS |
| 980 | |
▼a 201812
▼f 2019 |
| 990 | |
▼a 관리자 |