Search results

Short-term rentals (STRs) (like Airbnb) are reshaping social behaviour, notably in gastronomy, altering how people dine while travelling. This study delves into revenue management, examining the impact of seasonality and dining options near guests’ Airbnb. Machine Learning analysis of Airbnb data suggests owners enhance revenue strategies by adjusting prices seasonally, taking nearby food amenities into account.

This study analysed 220 Airbnb establishments from Madrid, Spain, using consistent monthly price data from Seetransparent and environment variables from MapInfo GIS. The Machine Learning algorithm calculated average prices, determined seasonal prices, applied factor analysis to categorise months and used cluster analysis to identify tourism-dwelling typologies with similar seasonal behaviour, considering nearby supermarkets/restaurants by factors such as proximity and availability of food options.

The findings reveal seasonal variations in three groups, using Machine Learning to improve revenue management: Group 1 has strong autumn-winter patterns and fewer restaurants; Group 2 shows higher spring seasonality, likely catering to tourists, and has more restaurants, while Group 3 has year-round stability, fewer supermarkets and active shops, potentially affecting local restaurant dynamics. Food establishments in these groups may need to adapt their strategies accordingly to capitalise on these seasonal trends.

Current literature lacks information on how seasonality, rental housing and proximity to amenities are interconnected. The originality of this study is to fill this gap by enhancing the STR price predictive model through a Machine Learning study. By examining seasonal trends, rental housing dynamics, and the proximity of supermarkets and restaurants to STR properties, the research enhances our understanding and predictions of STR price fluctuations, particularly in relation to the availability and demand for food options.

By merging good countryside and rural capitals frameworks, a model for reimagining the island's development is formulated, which is then applied to the female perspective to provide valuable insights from a group that is often marginalized in rural areas. As Croatian islands are highly tourism-oriented, this study finds it important to explore possibilities for future island development that can provide balanced and vibrant settlements on the islands.

The present paper synthesizes Shucksmith's (2018) model of a good countryside, which serves as a goal, with Gkartzios et al.'s (2022) capitals framework, which is viewed as a means of attaining a good countryside, specifically a good island. The research is delimited to the island of Brac, Croatia. By conducting interviews with female respondents, this study aims to capture the female perspective on envisioning potential futures of “good” island living, a perspective that is frequently underestimated despite its significant contributions to the creation of an ideal locale.

The results demonstrate that there is a substantial amount of socio-cultural rural capital that is leveraged to strengthen relatedness and rights as development objectives. However, low levels of economic, built and land-based rural capital pose challenges to achieving repair and re-enchantment, which are crucial for settlements that rely on tourism.

These findings bear immense implications for policymakers and planners, underscoring the imperative to account for the perspectives and needs of diverse social groups, including women, in the design and implementation of development strategies for islands. By doing so, a sustainable and equitable future, rich in tourism potential, can be cultivated on the island.

In the field of heritage science, especially applied to buildings and artefacts made by organic hygroscopic materials, analyzing the microclimate has always been of extreme importance. In particular, in many cases, the knowledge of the outdoor/indoor microclimate may support the decision process in conservation and preservation matters of historic buildings. This knowledge is often gained by implementing long and time-consuming monitoring campaigns that allow collecting atmospheric and climatic data.

Sometimes the collected time series may be corrupted, incomplete and/or subjected to the sensors' errors because of the remoteness of the historic building location, the natural aging of the sensor or the lack of a continuous check of the data downloading process. For this reason, in this work, an innovative approach about reconstructing the indoor microclimate into heritage buildings, just knowing the outdoor one, is proposed. This methodology is based on using machine learning tools known as variational auto encoders (VAEs), that are able to reconstruct time series and/or to fill data gaps.

The proposed approach is implemented using data collected in Ringebu Stave Church, a Norwegian medieval wooden heritage building. Reconstructing a realistic time series, for the vast majority of the year period, of the natural internal climate of the Church has been successfully implemented.

The novelty of this work is discussed in the framework of the existing literature. The work explores the potentials of machine learning tools compared to traditional ones, providing a method that is able to reliably fill missing data in time series.