Abstract
Missing data consists in the lack of information in a dataset and since it directly influences classification performance, neglecting it is not a valid option. Over the years, several studies presented alternative imputation strategies to deal with the three missing data mechanisms, Missing Completely At Random, Missing At Random and Missing Not At Random. However, there are no studies regarding the influence of all these three mechanisms on the latest high-performance Artificial Intelligence techniques, such as Deep Learning. The goal of this work is to perform a comparison study between state-of-the-art imputation techniques and a Stacked Denoising Autoencoders approach. To that end, the missing data mechanisms were synthetically generated in 6 different ways; 8 different imputation techniques were implemented; and finally, 33 complete datasets from different open source repositories were selected. The obtained results showed that Support Vector Machines imputation ensures the best classification performance while Multiple Imputation by Chained Equations performs better in terms of imputation quality. © Springer Nature Switzerland AG 2018.

Abstract

Abstract

Abstract
Although still little-known, glamping has become a nature-based tourism option for people who want a higher level of comfort. The offer of this type of accommodation is growing, namely in Portugal, but there are still few studies that address the motivations and other relevant factors explaining its adoption or refusal by consumers. The present study applied a qualitative approach aimed at exploring consumers’ motivations or obstacles for choosing glamping, and their perceptions as tourists on the differences between glamping and camping. Data were collected through the conduction of focus groups held in 2017 and content analysis techniques for contextualized interpretations were used. The most important motivational driver to go glamping is the direct contact with nature. Glamour, comfort, privacy and a different experience are also important aspects that consumers appreciate. Inversely, the main obstacles are the cost, the limited offer, the lack of knowledge, and the non-authenticity, compared to camping, of the offer.

Abstract
Guerrilla marketing is an innovative approach to communicate with customers and to capture their attention essentially due to its inherent creativity, unconventional media, and low cost. Despite the interesting contributions in the literature on this topic, most of what is known about guerrilla marketing is confined to its use and impact on consumers. This study aims to fill a gap identified in the guerrilla marketing literature by conducting an exploratory research study on the propensity of performing guerrilla marketing campaigns in a Business-to-Business (B2B) context. The research objectives of this paper are (i) identifying the perceptions of B2B managers on guerrilla marketing campaigns and (ii) exploring determinants of the adoption of guerrilla marketing campaigns targeted at corporate customers.We present the results of a qualitative research study comprising 12 semi-structured interviews with managers of different business areas. A content analysis was performed using Nvivo software.Participants in this study demonstrated that B2B managers recognize and value the advantages associated with guerrilla communication, which is in many instances seen as useful and viable for the B2B sector. The propensity for adoption is dependent on internal factors such as corporate culture, managers’ and collaborators’ profiles, risk-proneness, market share, and product innovativeness, but also on the sector’s usual practices of innovation and communication. Guerrilla marketing campaigns are more appropriate for attracting new B2B customers and need to be carefully adapted to the targets' profiles and preferences.

Abstract