Towards optimization of e-commerce search and discovery

Anjan Goswami, Chengxiang Zhai, Prasant Mohapatra

Research output: Contribution to journalConference article

Abstract

E-Commerce (E-Com) search is an emerging problem with multiple new challenges. One of the primary challenges constitutes optimizing multiple objectives involving business metrics such as sales and revenue and maintaining a discovery strategy for the site. In this paper, we formalize the e-com search problem for optimizing metrics based on sales, revenue, and relevance. We define a notion of item discoverability in search and show that learning to rank (LTR) algorithms trained with behavioral features from e-com customer interactions (eg. clicks,cart-adds, orders etc.) do not by themselves address the discoverability problem. Instead, a suitable explore-exploit framework must be integrated with the ranking algorithm. We thus construct a practical discovery strategy by keeping a few top positions for discovery and populating some of the items selected through exploration. Then, we present a few exploration strategies with low regret bounds in terms of business metrics. We conduct a simulation study with a synthetically generated dataset that represents items with different utility distribution and compares these strategies using metrics based on sales, revenue, relevance, and discovery. We find that a strategy based on adaptive submodular function based discovery framework can provide a nice balance of business metrics and discoverability compared to other strategies based on random exploration or multi-armed bandit. However, another strategy, based on monotonic submodular optimization function that needs to be integrated with linear LTR models also works well for discovery and has nice performances with respect to sales, revenue, and relevance.

Original languageEnglish (US)
JournalCEUR Workshop Proceedings
Volume2319
StatePublished - Jan 1 2018
Event2018 SIGIR Workshop On eCommerce, eCom 2018 - Ann Arbor, United States
Duration: Jul 12 2018 → …

Fingerprint

Sales
Industry
Electronic commerce

Keywords

  • Discoverability
  • E-com search
  • Exploration-exploitation
  • Learning to rank
  • Retrieval models

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Towards optimization of e-commerce search and discovery. / Goswami, Anjan; Zhai, Chengxiang; Mohapatra, Prasant.

In: CEUR Workshop Proceedings, Vol. 2319, 01.01.2018.

Research output: Contribution to journalConference article

@article{74d6c8d515114be0847aa111d692ecff,
title = "Towards optimization of e-commerce search and discovery",
abstract = "E-Commerce (E-Com) search is an emerging problem with multiple new challenges. One of the primary challenges constitutes optimizing multiple objectives involving business metrics such as sales and revenue and maintaining a discovery strategy for the site. In this paper, we formalize the e-com search problem for optimizing metrics based on sales, revenue, and relevance. We define a notion of item discoverability in search and show that learning to rank (LTR) algorithms trained with behavioral features from e-com customer interactions (eg. clicks,cart-adds, orders etc.) do not by themselves address the discoverability problem. Instead, a suitable explore-exploit framework must be integrated with the ranking algorithm. We thus construct a practical discovery strategy by keeping a few top positions for discovery and populating some of the items selected through exploration. Then, we present a few exploration strategies with low regret bounds in terms of business metrics. We conduct a simulation study with a synthetically generated dataset that represents items with different utility distribution and compares these strategies using metrics based on sales, revenue, relevance, and discovery. We find that a strategy based on adaptive submodular function based discovery framework can provide a nice balance of business metrics and discoverability compared to other strategies based on random exploration or multi-armed bandit. However, another strategy, based on monotonic submodular optimization function that needs to be integrated with linear LTR models also works well for discovery and has nice performances with respect to sales, revenue, and relevance.",
keywords = "Discoverability, E-com search, Exploration-exploitation, Learning to rank, Retrieval models",
author = "Anjan Goswami and Chengxiang Zhai and Prasant Mohapatra",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
volume = "2319",
journal = "CEUR Workshop Proceedings",
issn = "1613-0073",
publisher = "CEUR-WS",

}

TY - JOUR

T1 - Towards optimization of e-commerce search and discovery

AU - Goswami, Anjan

AU - Zhai, Chengxiang

AU - Mohapatra, Prasant

PY - 2018/1/1

Y1 - 2018/1/1

N2 - E-Commerce (E-Com) search is an emerging problem with multiple new challenges. One of the primary challenges constitutes optimizing multiple objectives involving business metrics such as sales and revenue and maintaining a discovery strategy for the site. In this paper, we formalize the e-com search problem for optimizing metrics based on sales, revenue, and relevance. We define a notion of item discoverability in search and show that learning to rank (LTR) algorithms trained with behavioral features from e-com customer interactions (eg. clicks,cart-adds, orders etc.) do not by themselves address the discoverability problem. Instead, a suitable explore-exploit framework must be integrated with the ranking algorithm. We thus construct a practical discovery strategy by keeping a few top positions for discovery and populating some of the items selected through exploration. Then, we present a few exploration strategies with low regret bounds in terms of business metrics. We conduct a simulation study with a synthetically generated dataset that represents items with different utility distribution and compares these strategies using metrics based on sales, revenue, relevance, and discovery. We find that a strategy based on adaptive submodular function based discovery framework can provide a nice balance of business metrics and discoverability compared to other strategies based on random exploration or multi-armed bandit. However, another strategy, based on monotonic submodular optimization function that needs to be integrated with linear LTR models also works well for discovery and has nice performances with respect to sales, revenue, and relevance.

AB - E-Commerce (E-Com) search is an emerging problem with multiple new challenges. One of the primary challenges constitutes optimizing multiple objectives involving business metrics such as sales and revenue and maintaining a discovery strategy for the site. In this paper, we formalize the e-com search problem for optimizing metrics based on sales, revenue, and relevance. We define a notion of item discoverability in search and show that learning to rank (LTR) algorithms trained with behavioral features from e-com customer interactions (eg. clicks,cart-adds, orders etc.) do not by themselves address the discoverability problem. Instead, a suitable explore-exploit framework must be integrated with the ranking algorithm. We thus construct a practical discovery strategy by keeping a few top positions for discovery and populating some of the items selected through exploration. Then, we present a few exploration strategies with low regret bounds in terms of business metrics. We conduct a simulation study with a synthetically generated dataset that represents items with different utility distribution and compares these strategies using metrics based on sales, revenue, relevance, and discovery. We find that a strategy based on adaptive submodular function based discovery framework can provide a nice balance of business metrics and discoverability compared to other strategies based on random exploration or multi-armed bandit. However, another strategy, based on monotonic submodular optimization function that needs to be integrated with linear LTR models also works well for discovery and has nice performances with respect to sales, revenue, and relevance.

KW - Discoverability

KW - E-com search

KW - Exploration-exploitation

KW - Learning to rank

KW - Retrieval models

UR - http://www.scopus.com/inward/record.url?scp=85062336832&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062336832&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85062336832

VL - 2319

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

ER -