改进的多层感知机在客户流失预测中的应用

针对在传统的客户流失预测数据预处理中，使用one-hot编码处理离散属性导致数据维度增加及数据过于稀疏的问题，提出了两种基于多层感知机的改进后的客户流失预测模型。其主要思想是分别使用堆叠自编码器和实体嵌入两种方法对多层感知机进行改进，通过将离散属性的高维编码数据向低维空间映射，有效地减少了one-hot编码产生的稀疏数据，增加了离散属性值之间的关联度。在对两份公开的数据集进行交叉验证后的实验结果表明，改进后的模型既有效地提高了预测的准确度，又维持了传统多层感知机模型在并行化计算方面的优势。     

Microblogging,friendship maintenance,and life satisfaction among university students: The mediatory role of online self-disclosure

Despite a substantial literature suggests that computer-mediated communication impact individuals’ various psychosocial factors, relatively few studies have elucidated the underlying mechanism behind these associations. Building upon self-disclosure theory and previous studies, the principal purpose of this present research is to systematically explore the relationships among microblog utilization, online self-disclosure, friendship maintenance, and perceived life satisfaction. A web-based survey was implemented using a total of 426 university students in Northwestern China. Structural equation modeling reveals that intensity of microblog use is positively associated with these students’ friendship maintenance and life satisfaction. Additionally, online self-disclosure plays the crucial mediatory role in the relationships between microblog use, quality of relationships, and gratification with life. The results imply that as microbloggers disclosure their inner thoughts or emotional states with other users online, they could foster their friendship maintenance and obtain greater life satisfaction. However, contrary to the expectation, students’ friendship maintenance is not discovered to be a significant predictor of the sense of life satisfaction in the online environment. Overall, these obtained outcomes of the empirical work could offer new insights into the deep comprehending of the social psychological process of microblogging among younger generation in the new media context.     

Specific smartphone uses and how they relate to anxiety and depression in university students: a cross-cultural perspective

ABSTRACT

People around the world spend hours of their daily lives using smartphones; therefore, it is important to conduct cross-cultural research on the effects of smartphone use on health and well-being as culture influences values, motivations and communication patterns. The purpose of this study was to explore 5 popular uses of the smartphone – messaging, browsing the Internet, posting social content, reading social content, and playing games – how they relate to anxiety and depression scores, and how they vary depending on the country of the participants: Spain, the United States, and Colombia. In all three countries the ranking of most popular uses was the same: (1) Messaging, (2) Reading social content, and (3) Browsing the Internet. In the USA, game playing contributed to anxiety scores whereas reading social content was a protective factor; regarding depression scores, text messaging was a contributing factor. In Spain, browsing the Internet contributed to anxiety scores; regarding depression scores, messaging was a contributing factor and posting social content was a protective factor. In Colombia, no specific use influenced anxiety scores; regarding depression scores, only game playing was a protective factor. Our results showed that in all the countries, problematic smartphone use contributed to anxiety scores.     

Rainbow over the Internet: How Internet use curtails homophobia in China

China, despite its rapid economic modernization and the lack of powerful conservative institutions, is not known for embracing diverse sexual orientation. The present study investigates whether and how Internet use, a increasingly important part of contemporary people's daily life, leads to changes in people's attitudes toward homosexuality in China, and relevant policy implications. Analyzing the Chinese General Social Survey data from 2010 to 2015, this paper develops an ordered probit model to quantify the influence of Internet use on homosexuality tolerance, adopts a substitution variable method to conduct the robustness check, and utilizes instrument variables to address the potential endogeneity in the regressions. The results show that Internet use has a significant positive impact on Chinese people's homosexuality tolerance. Further studies have found that the influence of Internet use on homosexuality tolerance is also heterogeneous to different populations. Besides, compared with traditional media, the Internet has a more significant impact on homosexuality tolerance. This paper provides some explanations for the rise in China's homosexuality tolerance from 2010 to 2015, and additional impetus for the international community to push for a liberal Internet policy in China.     

Responsive supply in fashion mass customisation systems with consumer returns

Mass customisation systems have been well-established in the fashion industry. Some fashion brands offer the mass customisation system for their selected seasonal products, and allow unconditional returns and full refund for any unsatisfied customers. Motivated by the above mentioned observed industrial practice and based on the growing importance of responsive supply, we explore in this paper the value of quick response supply in fashion mass customisation systems with consumer returns. We focus on investigating how the consumer returns rate affects (i) the optimal inventory decision of the fashion brand, (ii) the achievability of Pareto improvement in implementing quick response supply, (iii) the respective values of quick response for the fashion brand, the fashion supplier and also the fashion supply chain, and (iv) the impact of quick response supply on the environment. We interestingly find that consumer returns enhance the value of quick response supply to the fashion supplier. Quick response supply is also found to be helpful in reducing the environmental cost under the fashion mass customisation system with consumer returns.     

Developing English domestic occupancy profiles

ABSTRACT

Occupancy patterns are necessary to estimate energy demand and evaluate thermal comfort in households. Because of this, many European countries are developing representative domestic schedules to replace outdated criteria. This paper evaluates the state of knowledge of UK domestic occupancy patterns and develops new domestic occupancy profiles for England. The presented research (1) characterizes methods for collecting occupancy data and inferring patterns; (2) identifies and assesses the quality of categories of occupancy patterns used in building simulation; and (3) develops updated occupancy profiles. A systematic scoping review identified social and monitoring surveys as the most deployed data-collection methods. A systematic literature review also established that the occupancy categories most frequently used in UK building simulation are (a) a family with dependent children where the parents work full time; and (b) a retired elderly couple who spend most of their time indoors. The interview sample from the English Housing Survey 2014–15 was used to map household typologies. Results show that categories (a) and (b) combined amount to only 19% of England’s households, which suggest models are over-reliant on these groups. Considering this result, the paper develops occupancy patterns for England derived from 2015 UK Time Use Survey diaries for each household typology previously identified.     

Determinants of social gratifications obtained by older adults moderated by public supports for Internet access in Spain

As the standard of living constantly improves, and as life expectancy increases in developed countries, the number of adults who want to have a gratifying life increases as well. Furthermore, although the Internet offers a world of potentially rewarding experiences, there is much heterogeneity among older people with respect to those who are able to benefit from its use. To reduce this gap, public access and digital literacy programs have been implemented. The aim of the study was to find out the extent to which these programs moderate the effects of age and socioeconomic status on social access to and use of the Internet in a sample of older users in Spain. Through quota sampling of retired users over 54 years of age in Spain (N = 560), who were regular users of public supports for Internet access, a structural equation modeling and multi-group analysis was conducted. The data showed a staggered association of access indicators (physical access, digital skills and social e-activities) on the social gratifications obtained, as well as the moderating role of institutional supports. This study provides empirical evidence of the ability of public supports to moderate the effect of socioeconomics inequalities on access and social exploitation of the Internet by older people. The findings point to the need to strengthen digital literacy actions, especially in supports that are more sensitive to the effect of age and socio-economic status.     

Landscape dynamics of Mediterranean montane grasslands over 60 years and implications for habitats conservation. A case study in the northern Apennines (Italy)

Widespread trends of abandonment have strongly affected Mediterranean mountains after the Second World War, triggering spontaneous recolonisation of forests. A diachronic analysis of the landscape in a Natura 2000 site (Tuscany, Italy) was carried out using digital aerial photographs (1954, 2013) and a GIS-based methodology, focusing on territories above 1300 m a.s.l. The detected variations of total areas, patch shape, patch dimensions and selected metrics showed a notable shift of the vegetation towards woody types and a drastic reduction of open grasslands, some with high conservation value, accompanied by a strong increase in patch number, surface and edge. A decrease of SDI and SEI diversity indices was also observed. Considering that fragmentation is one of the main causes threatening habitats and species, our results point out a clear necessity for a monitoring programme and suitable actions aimed at improving the status of biodiversity-rich montane grasslands.     

Evaluation across and within collaborative manufacturing networks: a comparison of manufacturers’ interactions and attributes

Evaluation on collaborative manufacturing network (CMN) structure characteristics has important implications for network operations such as production decision-making, product recovery, creating consensus. Several recent studies suggest that augmenting network structure with nodes’ attributes can provide a more fine-grained understanding of the network. However, there have been few studies to provide a systematic understanding of these effects in a CMN at scale. This gap is bridged using an industrial printing machinery CMN data-set collected on a web-based producing and outsourcing service platform. Novel phenomena with respect to both interaction and attribute metrics across and within the CMNs are observed. Moreover, although many studies employ either interaction or attribute data to study the relative roles of manufacturers in a CMN, relatively little is known about the relationship between these two types of data. This study explores this relationship by comparing two defined metrics (i.e. relational capability and node capability), which evaluate the manufacturers’ interactions and attributes, respectively. We examine to what extent the two metrics of manufacturers correlate with each other, and how possible dissimilarities and similarities can be explained based on the collected industrial CMN data-set. The insights thereby provide a better basis for efficient operations decision-making in CMN.     

Validating the moderating role of age in multi-perspective acceptance model of wearable healthcare technology

The recent trend of aging population, not to mention the unprecedented pandemic, draws great attention from the general public about health concerns. Since healthcare information technology is different from non-healthcare information technology, additional contexts should be properly incorporated into technology acceptance research to accurately identify influential factors affecting the acceptance of wearable healthcare technology. Thus, we selectively reconfigured factors from health, privacy, and socio-demographic contexts to formulate a health-aware acceptance model. Then, it was empirically analyzed using structural equation modeling. Based on the results, whereas privacy concerns were directly associated with intention to use wearable healthcare technology, health concerns were not. Moreover, age had a moderating effect on social influence and facilitating conditions. These findings suggest valuable insights that the adoption rate of healthcare technology is increased by 1) keeping personal information securely, 2) facilitating social interaction among users, and 3) offering intuitive user experience for elderly people.