The popularity of on-demand ride pooling is owing to the benefits offered to customers (lower prices), taxi drivers (higher revenue), environment (lower carbon footprint due to fewer vehicles) and aggregation companies like Uber (higher revenue). To achieve these benefits, two key interlinked challenges have to be solved effectively: (a) pricing -- setting prices to customer requests for taxis; and (b) matching -- assignment of customers (that accepted the prices) to taxis/cars. Traditionally, both these challenges have been studied individually and using myopic approaches (considering only current requests), without considering the impact of current matching on addressing future requests. In this paper, we develop a novel framework that handles the pricing and matching problems together, while also considering the future impact of the pricing and matching decisions. In our experimental results on a real-world taxi dataset, we demonstrate that our framework can significantly improve revenue (up to 17\% and on average 6.4\%) in a sustainable manner by reducing the number of vehicles  (up to 14\% and on average 10.6\%) required to obtain a given fixed revenue and the overall distance travelled by vehicles (up to 11.1\% and on average 3.7\%). That is to say, we are able to provide an ideal win-win scenario for all stakeholders (customers, drivers, aggregator, environment) involved by obtaining higher revenue for customers, drivers, aggregator (ride pooling company) while being good for the environment (due to fewer number of vehicles on the road and lesser fuel consumed).

Future Aware Pricing and Matching for Sustainable On-demand Ride Pooling

The mobile communication enabled by cellular networks is the one of the main foundations of our modern society. Optimizing the performance of cellular networks and providing massive connectivity with improved coverage and user experience has a considerable social and economic impact on our daily life. This performance relies heavily on the configuration of the network parameters. However, with the massive increase in both the size and complexity of cellular networks, network management, especially parameter configuration, is becoming complicated. The current practice, which relies largely on experts' prior knowledge, is not adequate and will require lots of domain experts and high maintenance costs. In this work, we propose a learning-based framework for handover parameter configuration. The key challenge, in this case, is to tackle the complicated dependencies between neighboring cells and jointly optimize the whole network. Our framework addresses this challenge in two ways. First, we introduce a novel approach to imitate how the network responds to different network states and parameter values, called auto-grouping graph convolutional network (AG-GCN). During the parameter configuration stage, instead of solving the global optimization problem, we design a local multi-objective optimization strategy where each cell considers several local performance metrics to balance its own performance and its neighbors. We evaluate our proposed algorithm via a simulator constructed using real network data. We demonstrate that the handover parameters our model can find, achieve better average network throughput compared to those recommended by experts as well as alternative baselines, which can bring better network quality and stability. It has the potential to massively reduce costs arising from human expert intervention and maintenance.

Neighbor Auto-Grouping Graph Neural Networks for Handover Parameter Configuration in Cellular Network

Generating human mobility trajectories is of great importance to solve the lack of large-scale trajectory data in numerous applications, which is caused by privacy concerns. However, existing mobility trajectory generation methods still require real-world human trajectories centrally collected as the training data, where there exists an inescapable risk of privacy leakage. To overcome this limitation, in this paper, we propose PateGail, a privacy-preserving imitation learning model to generate mobility trajectories, which utilizes the powerful generative adversary imitation learning (GAIL) model to simulate the decision-making process of humans. Further, in order to protect user privacy, we train this model collectively based on decentralized mobility data stored in user devices, where personal discriminators are trained locally to distinguish and reward the real and generated human trajectories. In the training process, only the generated trajectories and their rewards obtained based on personal discriminators are shared between the server and devices, whose privacy is further preserved by our proposed perturbation mechanisms with theoretical proof to satisfy differential privacy. Further, to better model the human decision-making process, we propose a novel aggregation mechanism of the rewards obtained from personal discriminators. We theoretically prove that under the reward obtained based on the aggregation mechanism, our proposed model maximizes the lower bound of the discounted total rewards of users. Extensive experiments show that the trajectories generated by our model are able to resemble real-world trajectories in terms of five key statistical metrics, outperforming state-of-the-art algorithms by over 38.19%. Furthermore, we demonstrate that the synthetic trajectories are able to efficiently support practical applications, including mobility prediction and location recommendation.

PateGail: A Privacy-preserving Mobility Trajectory Generator with Imitation Learning

The concept of walkable urban development has gained increased
attention due to its public health, economic, and environmental
sustainability benefits. Unfortunately, land zoning
and historic under-investment have resulted in spatial inequality
in walkability and social inequality among residents.
We tackle the problem of Walkability Optimization through
the lens of combinatorial optimization. The task is to select
locations in which additional amenities (e.g., grocery stores,
schools, restaurants) can be allocated to improve resident access
via walking while taking into account existing amenities
and providing multiple options (e.g., for restaurants).
To this end, we derive Mixed-Integer Linear Programming
(MILP) and Constraint Programming (CP) models. Moreover,
we show that the problem’s objective function is submodular
in special cases, which motivates an efficient greedy
heuristic. We conduct a case study on 31 underserved neighborhoods
in the City of Toronto, Canada. MILP finds the
best solutions in most scenarios but does not scale well with
network size. The greedy algorithm scales well and finds
near-optimal solutions. Our empirical evaluation shows that
neighbourhoods with low walkability have a great potential
for transformation into pedestrian-friendly neighbourhoods
by strategically placing new amenities. Allocating 3 additional
grocery stores, schools, and restaurants can improve the
“WalkScore” by more than 50 points (on a scale of 100) for 4
neighbourhoods and reduce the walking distances to amenities
for 75% of all residential locations to 10 minutes for all
amenity types. Our code and paper appendix are available at
https://github.com/khalil-research/walkability.

Walkability Optimization: Formulations, Algorithms, and a Case Study of Toronto

As travel to participate in sport-events grows, Getz (2008) suggested participants are likely to engage in an event travel career (ETC) and their event and travel preferences change at different career stages (Buning & Gibson, 2016; Mirehie & Gibson, 2020). However, the ETC is not always linear and participants face competing priorities constraining their participation. The purpose of this study was to explore competing priorities as constraints encountered by four marathoner types associated with different ETC stages. Specifically, enduring involvement, running experience, and travel patterns of the four marathoner types were explored. Data were collected via an online survey. A total of N = 823 marathoners pursuing ETCs participated.

Factor analysis identified four dimensions of the enduring involvement scale: hedonic, centrality, social and identity. A competing priorities constraints scale was developed, revealing three dimensions: family responsibilities, finances and training time. MANOVA indicated the involvement level of marathoners progresses from Type 1 (novices) to Type 2 (intermediates) to Type 3 (experts) in hedonic and centrality. The impact of the training time constraint decreased from Type 1 (novices) to Type 2 (intermediates) to Type 3 (experts) marathoners. Type 3 (experts) marathoners showed the highest involvement level and were less confined by all the competing priorities constraints dimensions. Regrading running experience and travel patterns, descriptive statistics showed that running hours and miles in an average week significantly increased from Type 1 (novices) to Types 3 (experts). Specifically, higher involved runners (Type 3) have participated in marathon running and travel to marathon events for longer (years) than lower involved participants; they also participate in more marathons in an average year. The results may guide running club managers to help their members persist in marathon running by overcoming competing priorities constraints. Also, helping event organizers improve event planning to support marathoners in developing their ETCs.

Competing priorities constraints of marathoners in pursuing event travel careers

Taking a gap year and study abroad program has become popular in China. It is a trend that more Chinese backpackers taking long-term travel and sojourn abroad to see the world and pursue a new lifestyle. This study aims to explore the travel experiences of Chinese backpackers and expand the knowledge of backpacking. It intends to answer how is their travel and how they travel. 22 In-depth online interviews with travelers who have traveled for more than 1 year were conducted combined with their journal study. The findings show that Chinese backpackers perceive their travel as a way of life, a journey of connecting and exploring the world and self, training as well as interest. They enjoy the encounter and wander their life on the road with a strong interest in experiencing local life. Their experience can be divided into three themes: meeting people, learning about the culture, and experiencing life. They also presented different meanings of their travel include interaction, living a life they want, and self-development. Most of the backpacking studies still focus on western travelers or western perspectives while outbound Chinese backpackers are still unknown. As a new market force for many tourist destinations, it is necessary to understand Chinese backpackers and cater to their needs and behavior. Furthermore, different from other types of travel, long-term backpacking as a lifestyle is less explored. Further understanding of these evolving patterns of travel is needed. This study not only offers new insight into long-term backpackers and backpacking but also provides predictions for potential backpacker behavior and possible impact on the destination. The implication from their interaction and travel experience can benefit alternative tourism, niche tourism, or other types of tourism.

Long-term Chinese backpacker to the world: Experiences and meanings

Introduction: according to the report released by Ctrip and China Tourism Academy, 70% Chinese tourists bought group travel products in 2018 when travelling to Europe. However, how they evaluate the experiences after arriving home is not so clear in the literature. The research aims to reveal a holistic picture of how Chinese tourists assess their long-haul travel, not only including positive attributes, but more importantly negative attributes.

Methods: the online travel reviews on Ctrip consist of texts, pictures and tags such as departure date, posting date, travel mode (with whom to travel). They were collected over the year 2019 with destinations in Europe. All users’ reviews of each product have been categorized into three levels on the platform: good, intermediate and bad, therefore the positive and negative comments can be aggregated in separate pools. Content analysis, performed with R, sheds light on the factors attributing to both positive and negative reviews.

Results: after text mining, the factors that contribute to positive reviews will be crystalized. They are good configuration of itineraries, good services and explanation from the group’s guide, good value for money, and wonderful landscape. Conversely, defining bad factors which gave rise to negative reviews are the discrepancies between product description and reality in terms of hotel, guide, food, failure in fulfilling visa application and tax refund, forced shopping, experience of risks (e.g. robbery, unsafe driving), extra out-of-pocket items and change in predetermined routes or guide.

Discussion: the online reviews form e-word-of-mouth, which exerts a significant influence on potential customers. The findings of this study are significant in explaining which factors lead to positive and negative reviews of Chinese outbound group tourists. It is beneficial for tour operators in creating satisfying experiences and, to help the literature enrich both the positive and negative experience contributors.

Take-home reviews of Chinese group tourists

This study aimed to identify the constraints affecting the tourism sector of Dingalan, Aurora brought by the Covid-19 pandemic. It also aimed to assess the effectiveness of the intervention programs given by government and non-government institutions.

Study was focused on determining the socio-demographic profile of the respondents. Descriptive design of research was utilized, the data for evaluation were collected through questionnaire and interview.

Study revealed that, most of the respondents were at the age of 33 to 41 years old; majority were females; finished high school; earns 5,000- 8,000PhP; single and belonged to a family with 8-12 members. Souvenir makers/vendors was the top most occupation/source/s of income before and during the pandemic.

All respondents were very much agreed that the imposed curfew hours; lockdown; and age limit of travelers have resulted to the decrease in number of tourists. In relation to the aspect of financial constraints faced by the respondents, 100% were very much agreed that it affected their income negatively.

The Social Amelioration Program by the government aiming to help Filipinos during pandemic were highly regarded by the respondents, they were very much agreed that this program helped them financially. The technical assistance provided by the government was rated by the respondents as slightly agree. The non-government organizations according to the respondents did not provide any financial and technical assistance. Respondents rated the effectiveness of the intervention programs given by the government as moderately effective.

The researcher came up with the recommendations; the Local Government Unit may provide a long-term livelihood technical assistance to be able for respondents be equipped with technical skills to make their economic aspect in life sustainable. A comprehensive destination management plan may also be reviewed and revised to fit in the current situation adapting the new normal of travel and tourism.

Tourism during pandemic: Constraints and intervention in economic enterprise of the tourism sector in Dingaan, Aurora, Philippines

Distribution is a critical element of tourism marketing and management. While luxury travel is the fastest-growing segment of the tourism industry, almost all prior studies on tourism distribution channels (TDCs) have concentrated on the high-volume, low-price travel market. Therefore, this study seeks to fill this research gap by focusing on the characteristics of TDCs in the low-volume, high-end market from the perspective of outbound tour operators (OTOs).

Semi-structured in-depth interviews were conducted between December 2018 and September 2019. Respondents (n=23) were experienced specialists at the senior management level of luxury OTOs from various countries around the world. Interview questions are based on previous research and the lead author’s previous experience as a practitioner in the tourism industry.

Our analysis shows that luxury OTOs primarily approach travelers directly instead of through other intermediaries in order to be able to offer a seamless, safe, and extraordinary trip experience. Particularly word of mouth and referrals play an essential role. At destinations, most luxury OTOs attempt to shorten the TDC length by directly approaching service providers or DMCs to ensure arrangement flexibility, accuracy, and efficient communication with suppliers. The factors influencing luxury OTOs’ channel behaviors include accessibility, familiarity with the destination, communication convenience, and cost savings.

Because of the unique personalized needs of luxury travelers, luxury OTOs are disintermediating traditional travel agents, wholesalers, and inbound operators. Previous studies have analyzed the concept of disintermediation from the perspective of destination suppliers and the influence of the internet. In contrast, our findings indicate that disintermediation is a result of luxury OTOs’ response to the exclusive needs of upscale travelers. Consequently, luxury service providers should build direct and close relationships with OTOs and offer flexible and customized services to both OTOs and travelers.

Disintermediation in tourism distribution channels: The case of outbound tour operators in the luxury travel market

Introduction

The rapid growth ofinternational tourist arrivals in recent years has intensified individuals’ social capital.Social capital, comprising bonding, bridging and linking, is defined as an individual’s resources in social networks and ties (Elgar et al., 2011). Bonding- and bridging social capital are found to be critical to destination strategic planning (Souland et al., 2018). Differences are found in travel motivation and behaviours among generations (Nielsen, 2014). Furthermore, individuals’ social relationships with family members and friends are strengthened during and after the trip (Mura & Tavakoli, 2014). The present study aims to examine the social capital- travel motivation relationship.

Methods

This study adopted snowballing sampling approach which invited students and colleagues in a college to participate in an online questionnaire survey. They were also asked to invite a family member or friend to respond to the survey. 355 valid responses (260 females and 95 males) were used for statistical analysis.

Results

Table 1 shows that bonding social capital has significant and positive relationship with travel motives; the relationship of bridging and linking social capital to travel motivation are significantly and negatively related.

Table 1. Results for path coefficients 


Parameter Estimate t-values 
Travel motives<-Bonding social capital 0.674 4.286*** 
Travel motives<-Bridging social capital -.291 -2.504* 
Travel motives<-Linking social capital -.330 -4.648*** 

Note:*p<.05; ***p<.001

Discussion

The strong positive bonding social capital-travel motivation relationship reflects that individuals would like to go travel with their family members and good friends, thereby heightening his/her motivation to travel. Conversely, one’s association with dissimilar groups (e.g. casual acquaintances, work colleagues) and one’s lack of trust in government simultaneously inhibit his/her travel motives. The results imply that employers and government have responsibilities to reinforce ones’ social capital, to which tourism/travel marketers may design and offer relevant products/services accordingly.

The impact of social capital on travel motivation

Introduction:Air travel has been severely impacted by COVID-19 and recovery to pre-COVID-19 levels is predicted to take time. Millennials are an age group that had pre-COVID-19 more frequent holiday flyers than any other age group and carries – compared to elder age groups – a low risk of severe COVID-19 infections. It is therefore an interesting target group for airlines for recovery. The study identifies self-reported changes in flying behavior, travel motivations and travel fears of millennials after the COVID-19 pandemic.

Methods:The sample comprised 260 millennial travelers. Data was collected during May 2021 in Germany. Certain travel restrictions were still in place, such as mandatory quarantines for high-risk destinations, negative test prior to boarding and mask wearing during flight.

Results:A positive and significant relationship between the number of flights taken between March 2020 and today and the number of flights taken on average a year before COVID-19 (0.517) exists. Frequent travelers were more likely to feel safe traveling during the pandemic (0.271) and to fly during the next 6 months. Significant differences were found between males and females and particular motivations to travel post-COVID-19 (i.e., happiness, self-fulfillment, create new memories).

Discussion:Travel motivation of millennials often stem from a sustainability perspective. We investigate the motivations related to leisure, health & safety concerns. Airlines can target marketing to this age group and address fear of protection against infection. Price sensitivity of millennials has not changed, a desire for flexibility is visible. Finally, the findings of the present study suggest that gender-specific marketing strategies are warranted. The study findings point to the wider social implications of COVID-19 on the tourism industry. Limitations arise because respondents were predominantly female (68 %), university educated and did not belong to any COVID-19 risk group.

Will the experience of COVID-19 change flying behavior of millennials?

Purpose– The objective of the present study is to propose a comprehensive tourist ethnocentrism model by exploring the influence of tourist ethnocentrism on support for tourism development (STD), whether respondents perceived tourism as one having a positive effect in the local economy (ENP), and their intentions to travel domestically in the future.

Design/methodology/approach-An online survey created in Google Forms was employed to collect data for the present study. A convenient sample of Israeli respondents who are 18 years of age or older took part in the study. A total of 204 usable questionnaires were collected over the month of January 2021.SmartPLS was employed to test the proposed conceptual model and hypothesized relationships.

Findings-Findings suggest that tourist ethnocentrism is positively associated with support for tourism development. The study findings suggest that this relationship is moderated by gender. Furthermore, residents scoring high on the tourist ethnocentrism scale are more likely to associate tourist activity with positive contribution to the local economy. Finally, a positive relationship was observed between tourist ethnocentrism and intentions to travel domesticallydespite the risk associated with travel.

Originality/value–Thecurrent investigation contributes to the literature by proposing a model conceptualizing the influence of tourist ethnocentrism on both the attitudes and behavioral intentions of residents.

Underline digital video library

Future Aware Pricing and Matching for Sustainable On-demand Ride Pooling

Neighbor Auto-Grouping Graph Neural Networks for Handover Parameter Configuration in Cellular Network

PateGail: A Privacy-preserving Mobility Trajectory Generator with Imitation Learning

Walkability Optimization: Formulations, Algorithms, and a Case Study of Toronto

Competing priorities constraints of marathoners in pursuing event travel careers

Long-term Chinese backpacker to the world: Experiences and meanings

Take-home reviews of Chinese group tourists

Tourism during pandemic: Constraints and intervention in economic enterprise of the tourism sector in Dingaan, Aurora, Philippines

Disintermediation in tourism distribution channels: The case of outbound tour operators in the luxury travel market

The impact of social capital on travel motivation

Will the experience of COVID-19 change flying behavior of millennials?

Exploring the influence of tourist ethnocentrism on resident attitudes and behavioral intentions towards local travel

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES