Predictive potential of the bankruptcy global models in the tourism industry

Abstract

The globalisation process and the recent economic crises have increased the development of models to identify the factors related to business bankruptcy. The tourism industry is not immune to this concern, and in the previous literature, bankruptcy prediction models are generally focused on hotels or restaurants. However, there are no experiences of global models for tourism companies. This study develops a global bankruptcy prediction model capable of predicting any activities carried out in the tourism industry with high precision. To this end, a sample of 406 Spanish companies that have developed their activity in three tourism industry sectors (hotels, restaurants, and travel agencies) in the period 2017-2019 has been used. This sample includes bankrupt and non-bankrupt corporations and has allowed the comparison between a global model and various focused models applying artificial neural network techniques. The results have confirmed the superiority of the global model and provide different sample selection and cost minimisation solutions for bankruptcy prediction modelling in the tourism industry

Predicting bankruptcy using artificial intelligence: The case of the engineering industry

“…The AT indicator, reflecting asset utilization efficiency, was identified as a significant predictor of bankruptcy by Lee and Su (2015), Ogachi et al (2020), Sigrist and Leuenberger (2023). The NWC/TA is last significant indicator used by Altman (1968), Rafiei et al (2011), Valaskova et al (2018), Castillo García and Fernández Miguélez (2021, Sigrist and Leuenberger (2023).…”

“…The Table 2 shows that the studies focus on companies from different countries. The research samples of the mentioned studies consisted of manufacturing firms (Shin et al, 2005;Rafiei et al, 2011;Kim et al, 2018;Zoričák et al, 2020;Dube et al, 2023), firms operating in tourism industry (Youn and Gu, 2010;Bogdan, 2021;Castillo García and Fernández Miguélez, 2021), banks (Iturriaga and Sanz, 2015;Mishraz et al, 2021), heat supply firms (Horváthová et al, 2021), industrial firms (Callejón et al, 2013), firms from engineering and automotive industries (Gavurova et al, 2022), or not specified small or medium-sized companies (Yoon and Kwon, 2010;Ptak-Chmielewska, 2019;Calabrese, 2023). This paper contributes to the existing literature by constructing a bankruptcy prediction model for the engineering industry.…”

“…The ROA has been employed in prediction models since Altman (1968) and subsequently by Callejon et al (2013), Du Jardin (2018), Ptak-Chmielewska (2019), Tumpach et al (2020), Castillo García andFernández Miguélez (2021), Horváthová et al (2021), andDube et al (2023). Similarly, the ROE, defined by Fitzpatrick (1932) and emphasized by Lee and Su (2015), Ptak-Chmielewska (2019), Castillo García and Fernández Miguélez (2021), and Dube et al (2023, is deemed one of the most crucial predictors of bankruptcy. The AT indicator, reflecting asset utilization efficiency, was identified as a significant predictor of bankruptcy by Lee and Su (2015), Ogachi et al (2020), Sigrist and Leuenberger (2023).…”

A Literature Review on the Financial Determinants of Hotel Default

“…This fact can prohibit generating low p-values (Kalnins 2016), although with increasing data quality and the ability of methods to handle small numbers of default events (e.g., Ho et al (2013) use 12 default events and Sandin and Porporato (2008) use 11), these issues are gradually surpassed. On the other hand, del Castillo García and Fernández Miguélez (2021) and Laguillo et al (2019) question sector-specific models, as a sectoral approach can increase the costs of development and further maintenance and may not increase the accuracy significantly.…”