Search Results (25)

This study investigates the determinants of Airbnb prices in Athens and Thessaloniki, Greece, employing a hybrid approach combining econometric analysis, machine learning techniques, and artificial intelligence tools. Our findings highlight the significance of location, property type, host responsiveness, listing quality, and photograph quality in influencing rental prices. Notably, we leverage a publicly available AI tool to assess the esthetic and technical quality of listing photos, demonstrating its positive impact on rental prices. This underscores the increasing importance of visual marketing in the sharing economy and the democratization of AI tools for optimizing pricing strategies. We also conduct machine learning analysis, employing algorithms like Random Forest, k-Nearest Neighbors, Support Vector Machine, Neural Network, Gradient Boosting, and AdaBoost. Both AdaBoost and Gradient Boosting demonstrate strong performance across various metrics, with AdaBoost showing an advantage. The study offers valuable insights for Airbnb hosts, platform developers, and policymakers in understanding and optimizing pricing strategies within the short-term rental market. Full article

This study examines housing affordability trends in Central Europe, focusing on the Czech Republic, Slovakia, Austria, and Poland, in the wake of recent global disruptions including the COVID-19 pandemic, the 2021–2022 energy crisis, and the war in Ukraine. These events have intensified housing affordability challenges by driving up property prices, rental costs, and energy expenses. Using data from December 2022 to March 2023, the paper analyzes wage levels relative to housing costs in major cities—Prague, Brno, Bratislava, Vienna, Graz, Warsaw, and Kraków—through price-to-income and rent-to-income ratios. The findings reveal that affordability is most strained in Czech cities, particularly Prague, where property prices outpace wages, while Vienna demonstrates better affordability due to higher average incomes. The study integrates real estate platform data with official statistics and employs spatial mapping and exploratory econometric testing to identify affordability patterns and disparities. It concludes that affordability outcomes are shaped by wage dynamics, housing supply constraints, migration pressures, and policy responses. The study underscores the importance of targeted housing policies and wage interventions to address these challenges and highlights the need for cross-country policy learning and regional coordination to improve housing affordability and market resilience across Central Europe. Full article

The real estate market plays a pivotal role in most nations’ economy, showcasing continuous growth. Particularly noteworthy is the rapid expansion of the digital real estate sector, marked by innovations like 3D visualization and streamlined online contractual processes, a momentum further accelerated by the aftermath of the Coronavirus Disease 2019 (COVID-19) pandemic. Amidst this transformative landscape, artificial intelligence emerges as a vital force, addressing consumer needs by harnessing data analytics for predicting and monitoring rental prices. While studies have demonstrated the efficacy of machine learning (ML) algorithms such as decision trees and neural networks in predicting house prices, there is a lack of research specifically focused on rental property prices, a significant sector in Brazil due to the prohibitive costs associated with property acquisition. This study fills this crucial gap by delving into the intricacies of rental pricing, using data from the city of São Carlos-SP, Brazil. The research aims to analyze, model, and predict rental prices, employing an approach that incorporates diverse ML models. Through this analysis, our work showcases the potential of ML algorithms in accurately predicting rental house prices. Moreover, it envisions the practical application of this research with the development of a user-friendly website. This platform could revolutionize the renting experience, empowering both tenants and real estate agencies with the ability to estimate rental values based on specific property attributes and have access to its statistics. Full article

The COVID-19 pandemic has forced many accommodations to close. However, the pandemic might play an important role in providing an opportunity to achieve sustainable tourism with a good balance between housing for residents and accommodation for tourists. As the theoretical framework, this study aims to investigate the change in households triggered by accommodation closure due to the COVID-19 pandemic in Kyoto City’s historical center. Furthermore, the causes of these changes were examined by analyzing the real estate properties traded on the market. For the analysis, this study considered the COVID-19 pandemic as a natural experiment to investigate the causal relationship between the number of households, closed accommodations, and real estate properties. As a result, it was found that households increased by approximately 1.34 in neighborhood associations with closed simple accommodations. Regarding the causes of the increase, closed simple accommodation properties tend to change to short-term rentals. This study also highlighted that closed simple accommodations have significantly smaller room sizes than other property types, with only slightly higher prices. As a theoretical contribution, our findings suggest that the pandemic might have suppressed tourism gentrification, but increased the number of households. Full article

There has been very limited research conducted to predict rental prices in the German real estate market using an AI-based approach. From a general perspective, conventional approaches struggle to handle large amounts of data and fail to consider the numerous elements that affect rental prices. The absence of sophisticated, data-driven analytical tools further complicates this situation, impeding stakeholders, such as tenants, landlords, real estate agents, and the government, from obtaining the accurate insights necessary for making well-informed decisions in this area. This paper applies novel machine learning (ML) approaches, including ensemble techniques, neural networks, linear regression (LR), and tree-based algorithms, specifically designed for forecasting rental prices in Munich. To ensure accuracy and reliability, the performance of these models is evaluated using the R² score and root mean squared error (RMSE). The study provides two feature sets for model comparison, selected by particle swarm optimisation (PSO) and CatBoost. These two feature selection methods identify significant variables based on different mechanisms, such as seeking the optimal solution with an objective function and converting categorical features into target statistics (TSs) to address high-dimensional issues. These methods are ideal for this German dataset, which contains 49 features. Testing the performance of 10 ML algorithms on two sets helps validate the robustness and efficacy of the AI-based approach utilising the PyTorch framework. The findings illustrate that ML models combined with PyTorch-based neural networks (PNNs) demonstrate high accuracy compared to standalone ML models, regardless of feature changes. The improved performance indicates that utilising the PyTorch framework for predictive tasks is advantageous, as evidenced by a statistical significance test in terms of both R² and RMSE (p-values < 0.001). The integration results display outstanding accuracy, averaging 90% across both feature sets. Particularly, the XGB model, which exhibited the lowest performance among all models in both sets, significantly improved from 0.8903 to 0.9097 in set 1 and from 0.8717 to 0.9022 in set 2 after being combined with the PNN. These results showcase the efficacy of using the PyTorch framework, enhancing the precision and reliability of the ML models in predicting the dynamic real estate market. Given that this study applies two feature sets and demonstrates consistent performance across sets with varying characteristics, the methodology may be applied to other locations. By offering accurate projections, it aids investors, renters, property managers, and regulators in facilitating better decision-making in the real estate sector. Full article

In the competitive landscape of Airbnb hosting, optimizing pricing strategies for properties is a complex challenge that requires revenue maximization with high occupancy rates. This research aimed to introduce a solution that leverages big data and machine learning techniques to help hosts improve their property’s market performance. Our primary goal was to introduce a solution that can augment property owners’ understanding of their property’s market value within their urban context, thereby optimizing both the utilization and profitability of their listings. We employed a multi-faceted approach with diverse models, including support vector regression, XGBoost, and neural networks, to analyze the influence of factors such as location, host attributes, and guest reviews on a listing’s financial performance. To further refine our predictive models, we integrated natural language processing techniques for in-depth listing review analysis, focusing on term frequency-inverse document frequency (TF-IDF), bag-of-words, and aspect-based sentiment analysis. Integrating such techniques allowed for in-depth listing review analysis, providing nuanced insights into guest preferences and satisfaction. Our findings demonstrated that AirBnB hosts can effectively utilize both state-of-the-art and traditional machine learning algorithms to better understand customer needs and preferences, more accurately assess their listings’ market value, and focus on the importance of dynamic pricing strategies. By adopting this data-driven approach, hosts can achieve a balance between maintaining competitive pricing and ensuring high occupancy rates. This method not only enhances revenue potential but also contributes to improved guest satisfaction and the growing field of data-driven decisions in the sharing economy, specially tailored to the challenges of short-term rentals. Full article

In the accommodation field, reasonable pricing is crucial for hosts to maximize their profits and is also an essential factor influencing tourists’ tendency to choose. The link between price prediction and findings about the causal relationships between key indicators and prices is not well discussed in the literature. This research aims to identify comprehensive pricing determinants for sharing economy-based lodging services and utilize them for lodging price prediction. Utilizing data retrieved from InsideAirbnb, we recognized 50 variables classified into five categories: property functions, host attributes, reputation, location, and indispensable miscellaneous factors. Property descriptions and a featured image posted by hosts were also added as input to indicate price-influencing antecedents. We proposed a price prediction model by incorporating a fully connected neural network, the bidirectional encoder representations from transformers (BERT), and MobileNet with these data sources. The model was validated using 8380 Airbnb listings from Amsterdam, North Holland, Netherlands. Results reveal that our model outperforms other models with simple or fewer inputs, reaching a minimum MAPE (mean absolute percentage error) of 5.5682%. The novelty of this study is the application of multimodal input and multiple neural networks in forecasting sharing economy accommodation prices to boost predictive performance. The findings provide useful guidance on price setting for hosts in the sharing economy that is compliant with rental market regulations, which is particularly important for sustainable hospitality growth. Full article

Since 2008, the company Airbnb has brought significant changes to the hospitality industry worldwide. Experiencing remarkable growth, it currently offers over six million listings in 191 countries across one hundred thousand cities. Airbnb has gained immense popularity among travellers seeking accommodations globally. Consequently, Airbnb generates extensive datasets from its listings that contain rich features that have captured the attention of researchers. These datasets offer potentially valuable information that can be extracted to greatly assist individuals and governments in making more informed decisions. Pricing rental properties on Airbnb still presents a challenge for owners, as it directly impacts customer demand. This research aimed to conquer the challenge by developing a sustainable price prediction model for Airbnb listings by incorporating property specifications, owner information and customer reviews. By utilising this model, owners can estimate the expected value of their Airbnb listings. We trained and fine-tuned several machine learning models using an Airbnb listing dataset from Barcelona. Performance evaluation metrics, such as mean squared error (MSE), mean absolute error (MAE), root mean square error (RMSE) and $R^2$ score were then used to compare the models. To enhance the performance of the predictive models, sentiment analysis was used to extract relevant features from customer reviews. Feature importance analysis was also conducted to determine which attributes were the most influential on listing price predictions. The results show that the Lasso and Ridge models outperformed the others considered in the study, with an average $R^2$ score of 99%. We found that amenities-related features had a negligible impact on all models’ performance. The most significant features found were polarity (positive/negative sentiment), the number of bedrooms, the accommodation’s maximum capacity, the number of beds and the quantity of reviews received by the listing in the past 12 months, respectively. We found that certain room types (categorized as entire home/apartment, private room or shared room) are associated with lower predicted prices. Full article

The concept of smart sustainable cities—as a favorable response to different challenges faced in urban areas—is rapidly gaining momentum and worldwide attention. This trend has driven the exploration of various technologies to improve the utilization of limited resources and idling capacities (i.e., underutilized physical assets such as buildings or facilities). In fact, a new business model has been introduced recently to smart cities, known as “shared economy”. The shared economy is a socioeconomic system that enables intermediary exchanges of goods and services between people and/or organizations, which boosts productivity and leverages underutilized resources to maximum potential. However, one of the inherent issues hindering the wide adoption of shared economy systems is the lack of trust between the providers and users of such systems. To this end, this study focuses on long-term shared properties/buildings and proposes an intelligent, IoT-enabled device and dynamic pricing model to address the issue of information asymmetry. First, 10 indicators were identified to assess the condition of the shared property. Next, multiple sensors were used, calibrated, and integrated into an IoT-enabled sensing device where the collected data was combined using intelligent sensor fusion technologies in a real-time manner. Third, a survey was developed and distributed to examine the significance of the 10 indicators, and an innovative reliability index was created accordingly to reflect the overall condition of the shared property. Fourth, a dynamic pricing model was developed to reward condition-conscious property users and penalize condition-unconscious ones. To ensure applicability and robustness of the proposed device and model, a pilot project was implemented in a smart long-term rental property in Newark, NJ, United States. Ultimately, this research provided insights on how to improve the operational efficiency of shared economy systems by offering (1) the providers of shared properties visibility over the condition of their properties through real-time assessment of the user reliability, and (2) the users of shared properties assured safety and monetary incentives to maintain the shared environment in a good condition. Full article

The sharing economy relating to e-hospitality is threatened globally with sanctions and closure owing to incessant noise and partying complaints, as well as complaints relating to reckless driving, tax evasion, and its social and economic effect on residents and accommodation vendors of longer stay rentals. Because the government is seeking a balance in regulating the e-hospitality sector, we sought to explore how professionalism of the e-hospitality platforms could potentially contribute to the sustainable growth of the sector in local and regional communities. In our study we developed a conceptual narrative that distinguishes two dimensions of professionalism for the sharing economy, namely the ticket clipper and end-to-end model. Data for the research was obtained from Vacation Rental Data (Airdna). Airdna provides a databank for both Airbnb and VRBO/Stayz. For the study a dataset from Airdna for HomeAway, also popularly known as Stayz, was utilized as a representative sample from a tourism town in Western Australia. For analysis of the dataset, path/panel regression was utilized, with a hierarchical linear model subsequently adopted for cross-section and multi-sectional analysis. Findings in the study demonstrate that professionals tend to improve the overall rating, and where the overall rating mediates the relationship between management firm (property/apartment/accommodation venue) and price. It was further observed that no relationship exists between overall rating and the number of HomeAway supply types; nevertheless, professionals promote the image and reputation of the property. Contrary, bad, or negative e-hospitality reviews lead to avoidance by prospective visitors. Lastly, results from the study took the form of two theoretical contributions, namely the ticket clipper model and the end-to-end model. More complaints were received concerning ticket clippers and it was noted that this model has caused severe shutdown in several cities and regions. The end-to-end model appears to be more sustainable. Moreover, literature suggests that there are more complaints from residents concerning ticket clippers and it was noted that this model has caused severe shutdown in several cities, nonetheless the end-to-end model appears to be more sustainable. Full article

The article compares the effects of crisis on the real estate market in two regions of the Czech Republic that differ from a macroeconomic point of view. The region of Prague represents the rich and developed region while the Karlovy Vary region struggles with many socio-economic and structural problems. An analysis was performed for the time period of 2018 to 2022. It analyzed the development of apartment prices in both regions, the availability of housing, the turnover of the real estate market in terms of the number of apartment sales, the development of liens on real estate, the number of apartment transfers from state property to private ownership, and the development of the number of real estate foreclosures. The basis for creating statistical outputs is the EVAL software, which was developed by one of the co-authors of this article. The EVAL software collects price offers of apartments offered for sale and rent throughout the Czech Republic and collects publicly available data from the cadastral office. The authors found that the real estate market experienced a significant turnaround in the volume of mortgage loans granted in 2022. This decline led to a significant drop in the total volume of real estate transactions. The findings suggest that potential buyers should wait for property prices to drop before buying, while rental property owners and investors can take advantage of the increased demand for properties. Full article

The private housing rental market has rapidly developed and demonstrated its outstanding contribution to improving affordability for the floating population in China. However, the forming pattern of private housing rental prices (PHRP) remains poorly understood in China’s highly dense populated cities. This study aims to comprehensively investigate the determinants of PHRP and depict their spatial pattern, considering the diverse functions of different areas within the city. A theoretical framework of the factors that influence PHRP has been developed based on an extensive literate study. Taking Chongqing city as a case, a Multiscale Geographically Weighted Regression (MGWR) analysis based on data from Lianjia.com and 58.com was conducted to investigate the spatial pattern of those influencing factors. The PHRP in Chongqing were mainly shaped by the factors of traffic condition and the neighborhood environment. The main findings highlighted that the influence of traffic condition on rental prices is more dominating in the industrial and financial zones, and the neighborhood factors represent spatial heterogeneity in the educational and commercial zones. This study provides a comprehensive examination of the spatial pattern of PHRP’s determinants in highly dense populated Chinese cities, extending the understanding of factors influencing housing rental prices. Practically, it provides scientific and reliable recommendations for the local governments and housing agencies in developing housing properties that consider the needs of the floating population. Moreover, tenants in highly dense populated cities benefit from suggestions about looking for proper accommodation with high value and accessibility in different functional zones of the city. Full article

The increasing growth of population living in cities, associated with the commoditization of investment in real estate, has impacted real estate prices and created obstacles for average income families to meet their housing needs. This problem is generalized to virtually all cities, but it has assumed larger proportions in cities where economic activities (tourism, financial services, high-tech industry) have flourished after the financial crisis. Lisbon is one of those cases. The growth of short-term rentals led to an increase in the property prices well above the average income growth, eroding housing affordability. This paper will focus on analyzing Lisbon´s affordability and understanding its main determinants. The analysis is carried out from the compilation and processing of data from 2004 to 2019, in the context of the municipality of Lisbon, using statistical instruments of linear regression in an exploratory and predictive approach. The results suggest a great influence of factors such as tourism, the foreign population with resident status, the propagation of short-term rentals and public policies on the worsening of housing affordability. In view of these conclusions, the preponderance of the type of public policies implemented and their relationship with the most prominent factors on housing affordability is debated. Full article

This paper aims to examine the responses of commercial real estate markets to COVID-19 and the implications for post-pandemic cities. Using data of Florida’s metropolitan areas in a fixed effect regression model, we find that sales volumes of retail properties decline instantly under the shock of COVID-19 but are followed by a strong recovery after one quarter. Meanwhile, COVID-19 depresses the growth rate of rent for office property, but the impact is short-term, and the office rental market bounces back to about 70 percent one quarter later. In comparison, industrial properties witness a rise in the growth rate of sales and rent price. Results indicate that urban planners may consider adjusting the amount of lands allocated to different usages to meet the evolving demands of urban space in the post-pandemic era. Full article

Multi-modal data are widely available for online real estate listings. Announcements can contain various forms of data, including visual data and unstructured textual descriptions. Nonetheless, many traditional real estate pricing models rely solely on well-structured tabular features. This work investigates whether it is possible to improve the performance of the pricing model using additional unstructured data, namely images of the property and satellite images. We compare four models based on the type of input data they use: (1) tabular data only, (2) tabular data and property images, (3) tabular data and satellite images, and (4) tabular data and a combination of property and satellite images. In a supervised context, the branches of dedicated neural networks for each data type are fused (concatenated) to predict log rental prices. The novel dataset devised for the study (SRED) consists of 11,105 flat rentals advertised over the internet in Switzerland. The results reveal that using all three sources of data generally outperforms machine learning models built on only tabular information. The findings pave the way for further research on integrating other non-structured inputs, for instance, the textual descriptions of properties. Full article