Marketing Segmentation and Targeted Marketing for Tourism

Liu Ye Xin, Li Yiteng, Ritika Jain, Tran Thi Hong Van, William Lim () and Zhao Yilin
Additional contact information
Liu Ye Xin: Nanyang Technological University
Li Yiteng: Nanyang Technological University
Ritika Jain: Nanyang Technological University
Tran Thi Hong Van: Nanyang Technological University
William Lim: Nanyang Technological University
Zhao Yilin: Nanyang Technological University

A chapter in Tourism Analytics Before and After COVID-19, 2023, pp 139-155 from Springer

Abstract: Abstract In this work, we carried out descriptive analytics on tourism data before and during the pandemic. In brief, all sectors of the tourism industry which includes food and beverage, shopping, and accommodation fell about 70% on average. This is more than half of the usual revenue. As the solution lies within the domestic market for the mid term, a closer look was the country’s demographics and household expenditure. Through observation of household expenditure on tourism, there was a natural progression to the use of classification methods to identify clusters that can contribute to the recovery of the tourism industry. This led to the creation of a series of models that aim to benefit businesses through the efficient use of marketing resources. The recommended solution is divided into two main categories: market segmentation and targeted marketing. The former involves the use of classification methods, and the latter uses machine learning models to funnel down to customers who have a high probability of converting. In market segmentation, classification modeling was applied for better hotel recommendations and increased spending in shopping malls. Through the grouping of customer profiles, both scenarios saw a potential increase in targeting performance in the range of 10–20%. As for the efficient use of marketing resources through better targeting, conversion is achieved through placing the right advertisements to the right audience. The models use K-Nearest Regression, Logistic Regression, Decisions Trees, and Support Vector Machine. On average, the models are able to double the rate at which an audience clicks on an advertisement, for more efficient use of advertising resources. We estimate potential savings for industry wide to be about SGD 45 million. In terms of marketing strategy, identifying the market segments will come before the use of efficient ad-targeting models.

Date: 2023
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-981-19-9369-5_9

Ordering information: This item can be ordered from
http://www.springer.com/9789811993695

DOI: 10.1007/978-981-19-9369-5_9

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().