Using machine learning and big data for efficient forecasting of hotel booking cancellations

Cancellations are a key aspect of hotel revenue management because of their impact on room reservation systems. In fact, very little is known about the reasons that lead customers to cancel, or how it can be avoided. The aim of this paper is to propose a means of enabling the forecasting of hotel booking cancellations using only 13 independent variables, a reduced number in comparison with related research in the area, which in addition coincide with those that are most often requested by customers when they place a reservation. For this matter, machine-learning techniques, among other artificial neural networks optimised with genetic algorithms were applied achieving a cancellation rate of up to 98%. The proposed methodology allows us not only to know about cancellation rates, but also to identify which customer is likely to cancel. This approach would mean organisations could strengthen their action protocols regarding tourist arrivals.     

Efficiency evaluation of China's high-tech industry with a multi-activity network data envelopment analysis approach

This paper employs a Russell multi-activity network DEA model and divides the overall innovation process into the upstream Research and Development (R&D) process and the downstream commercialization process to appraise the innovation performance of China's high-tech industries from 2009 to 2013. This model can deal with the problems of intermediates, shared inputs and slack-based measure in a unified framework, and the result can provide policy makers with process-specific information on how to improve the innovation performance of China's high-tech industries. The main findings are presented as follows. First, the overall efficiency of China's high-tech industries still remains at a low level, which has its roots mainly in commercialization inefficiencies other than R&D inefficiencies. Second, for most provinces, their R&D efficiencies do not match up with their commercialization efficiencies. Finally, the innovative activities of China's high-tech industries should be driven by the market demand -oriented for the improvement of innovation efficiency.     

FREE VERSUS SECOND‐BEST ENTRY IN COURNOT OLIGOPOLIES WITH FIRM‐SPECIFIC NETWORKS

This paper endogenizes the number of firms in an industry with positive network effects, complete incompatibility, and firms that compete in quantity. To this end, we compare two possibilities: free entry and second‐best number of firms (the one that maximizes social welfare). We show that with business‐stealing competition, free entry yields, in general, more firms than the socially optimal solution. In addition, we find that by the nature of the industry with firm‐specific networks, total production may be greater or lower under free entry than with a regulator; moreover, some industries attain their maximum social welfare with a monopoly.     

External funding of major capital projects in the UK Higher Education sector: issues of demand,supply and market timing?

The aim of this paper is to consider the sources of finance used to support major capital expenditure in the UK Higher Education sector and to reflect on any differences between traditional corporate finance theory and practice in the UK university sector. Utilising both HESA data returns and published annual accounts, an in-depth analysis using a logit structure is carried out on data from the top 63 UK universities over the period 2014–2017, to establish the range of funding sources adopted for major capital projects, all set within the context of the UK macro environment and a period of low interest rates. The research also carries out a survey of funders to understand the decision criteria used by lenders active in the Higher Education sector and a survey of university finance directors to determine the use of the funds, the reasons behind past lending decisions and to ascertain likely future demand for finance to fund major capital projects.     

基于跨国并购的创新网络嵌入、网络异质性与创新质量研究

区别于现有研究通常将跨国并购视为一个“事件”研究其对并购企业技术创新的影响，基于创新网络视角，文章采用中国上市公司数据，通过关系嵌入和结构嵌入两个维度探讨基于跨国并购的国外创新网络对创新质量的影响机制。研究发现，通过跨国并购嵌入创新网络的直接联系促进了创新质量提升，间接联系和结构洞对创新质量产生了显著的抑制效应。网络异质性对基于跨国并购的创新网络嵌入与创新质量具有倒U型调节作用，在网络异质适度阶段，网络异质性正向调节基于跨国并购的创新网络嵌入的创新质量效应，在网络异质过度阶段，网络异质性具有负向调节效应。研究发现为新兴经济体企业实施跨国并购，有效嵌入国外创新网络，配置创新资源，提升创新质量，提供了有价值的参考。     

Ad hoc网络中基于多波束天线的集中式低时延调度算法

UxDMA算法是一种高效的集中式算法，是用于时分多址、频分多址和码分多址信道分配的统一算法。在UxDMA的基础上，利用多波束天线的多波束形成能力，针对低时延定向ad hoc网络提出了一种集中式调度算法——CLSM(Centralized Low-delay Scheduling Algorithm Based on Multi-beam Antennas)。CLSM通过不同时延等级限制的报文来比较着色后发送链路的优先级，优先选择高优先级链路传输。通过仿真验证了CLSM的性能：与UxDMA相比，该算法在多时延限制的发送端调度中表现出了更好的吞吐量和时延性能。     

Sensory Aspects of Retailing: Theoretical and Practical Implications

Sensory elements are an important aspect of both offline and online retail stores and can non-consciously influence consumer judgments and purchase behavior. In offline settings, ambient factors like scent, lighting, and music have been shown to influence customers’ shopping experiences and their buying behaviors. For online retail outlets, sensory factors related to color, display patterns, and layouts can have significant effects on consumer behavior. Sensory elements have strong managerial relevance since they can non-consciously influence behaviors and because they are relatively easy to change; for example, it requires minimal effort to change the lighting or the music at a physical retail store or the display pattern for an online store. The eight papers in this special issue address theoretical and practical issues related to how different sensory elements can strongly influence retail practices. These papers focus on underexplored topic areas and also on emerging technologies, which stimulate thoughts for further research in these areas.     

中国数字经济空间关联网络及其影响因素分析

基于2013年和2020年29个省的数据，用因子模型测算各省数字经济发展水平，在此基础上使用修正引力模型构建数字经济空间关联网络，并深入分析此网络特征。结果表明：中国数字经济发展水平存在差异，东部地区高于中西部地区；中国数字经济空间关联网络密度不断增大；北京、山东、江苏一直是网络的重要输出省份，近年来西部地区在网络中的作用越来越明显；地理位置相邻、贸易开放度和产业结构对网络的形成有显著影响。     

基于机器学习的斜坡堤越浪量预测方法研究

针对斜坡堤越浪量预测方法,分别建立集成神经网络(ensemble neural network,ENN)、随机森林(random for-eset,RF)和支持向量回归机(suppport vector regression,SVR)3种机器学习模型对斜坡堤越浪量进行预测,并利用决定系数R2和均方根误差RMSE来评估模型性能.最后,对3种模型的性能进行分析.结果显示,集成神经网络模型的决定系数R2和均方根误差RM S E分别约为0.96和0.0018,随机森林模型的决定系数R2和均方根误差RMSE分别约为0.97和0.0014,支持向量回归机模型的决定系数R2和均方根误差RMSE分别约为0.94和0.002.对比发现,3种模型的决定系数都达到0.9以上,都具有较高的预测精度,随机森林相比其他两个模型精度更高.