Purpose This study aims to predict hotel demand through text analysis by investigating keyword series to increase demand predictions’ precision. To do so, this paper presents a framework for modeling hotel demand that incorporates machine learning techniques. Design/methodology/approach The empirical forecasting is conducted by introducing a segmented machine learning approach of leveraging hierarchical clustering tied to machine learning and deep learning techniques. These features allow the model to yield more precise estimates. This study evaluates an extensive range of social media–derived words with the most significant probability of gradually establishing an understanding of an optimal outcome. Analyzes were performed on a major hotel chain in an urban market setting within the USA. Findings The findings indicate that while traditional methods, being the naïve approach and ARIMA models, struggled with forecasting accuracy, segmented boosting methods (XGBoost) leveraging social media predict hotel occupancy with greater precision for all examined time horizons. Additionally, the segmented learning approach improved the forecasts’ stability and robustness while mitigating common overfitting issues within a highly dimensional data set. Research limitations/implications Incorporating social media into a segmented learning framework can augment the current generation of forecasting methods’ accuracy. Moreover, the segmented learning approach mitigates the negative effects of market shifts (e.g. COVID-19) that can reduce in-production forecasts’ life-cycles. The ability to be more robust to market deviations will allow hospitality firms to minimize development time. Originality/value The results are expected to generate insights by providing revenue managers with an instrument for predicting demand.

Purpose The purpose of this paper is to investigate how using social media (SM) as a tool to influence demand motivates the distribution of different price promotion strategies to encourage consumers to utilize direct bookings, along with how this impacts revenue strategies and profitability. Design/methodology/approach This study surveyed hotel executives who hold managerial positions and revenue managers with a direct influence on pricing decisions and developed multiple regression analysis models for various pricing approaches. Findings This study confirms the relationship between distribution channels and dynamic pricing strategies, although the same is not true with respect to traditional pricing techniques. The authors found that the adoption of SM as a strategic tool provides a platform to promote tactical revenue management strategies and to practice differential pricing motives. Originality/value The findings of the study will help hotel revenue managers to take into account a new way of thinking – namely, an interactive response to consumers’ preferences to improve profitability, based on different pricing methods distributed through SM. In this context, SM has elevated pricing strategies to a new and particularly challenging level.

No abstract

Purpose The online travel environment continues to expand as the numerous peer-to-peer (P2P) marketplaces that comprise the “sharing economy” have also multiplied and expanded, resulting in a move from the traditional hospitality industry to a new digital ecosystem. The purpose of this paper is to examine the effects of different antecedents and the relationships between benefit factors. It does so by simulating the behavior that leads to consumer loyalty and repurchase intentions within a P2P marketplace transaction. Design/methodology/approach The analysis is based on survey data from 456 respondents located in different regions, collected via a web-based survey questionnaire. A two-step approach employing confirmatory factor analysis, followed by structural equation modeling, was conducted to evaluate the measurement and structural models, as recommended by Anderson and Gerbing. Findings The findings of this study partially confirm the relationship between benefit factors (monetary, hedonic and location benefits) and consumer repurchase intentions. The benefit factors display a positive influence on consumer satisfaction, which mediates the relationship between loyalty and repurchase intentions. Hence, the study contributes to scholarly efforts to better understand why consumers choose to purchase through P2P platforms. Practical implications The findings of this study can provide P2P intermediaries and hosts with the empirical evidence of consumer behavioral changes. Nowadays, in practice, consumers have the ability to compare products and offers. As such, for a consumer to remain loyal to a particular supplier, the offer must satisfy the service and experience that the consumer has in mind, as many alternative offers exist. Originality/value This study seeks to identify the behavioral factors that cause even loyal consumers to move from the traditional hospitality industries to P2P platforms, despite the probability of losing any loyalty benefits gained in the traditional industries.

Demand uncertainty is a fundamental characteristic of the hospitality industry. Hotel room inventory is fixed, and devising an accurate daily demand measurement is a key operational challenge. In practice, it is difficult to predict the industry stability and capture demand uncertainty, so the industry relies on demand estimates. This process of estimation affects revenue maximization, as it is sensitive to incremental costs. In this article, we implemented vector autoregressive (VAR) models and compared them to the Bayesian VAR to examine the accuracy of predicting demand. We evaluated the results using a new measure of forecasting accuracy, the mean arctangent absolute percentage error (MAAPE). The results generated from the forecasts confirm the significant improvement in forecasting performance that can be obtained using the Bayesian model. It is noteworthy that the VAR performs the best for the lower horizons. The results also suggest that MAAPE outperforms other existing accuracy measures, in terms of error rates.