A fast and scalable ensemble of global models with long memory and data partitioning for the M5 forecasting competition

This work presents key insights on the model development strategies used in our cross-learning-based retail demand forecast framework. The proposed framework outperforms state-of-the-art univariate models in the time series forecasting literature. It has achieved 17th position in the accuracy track of the M5 forecasting competition, which is among the top 1% of solutions.     

水生态系统服务供需视角下的水网乡村 适应性规划策略——以吴江张鸭荡片区为例

苏南乡村地区一直是中国乡村建设的先行区域，特殊的纵横交错的水网结构构成了一个错综复杂的系统，呈现出其他地区不具有的复杂性和生态特殊性。随着城镇的扩张，乡村的发展建设使其水网空间的平衡发展面临极大的挑战。传统单一静态的规划方法逐渐显示出无法适应经济、社会等发展要求的缺陷。苏南乡村地区以水为核心，从水生态系统服务供需关系的视角下探究水网乡村的适应性规划策略更加适应当前的乡村现状和需求。以传统水网乡村空间形态转译为基础，建立水生态系统供需服务评估体系，在评估水生态系统服务供需能力的基础上，分析供需分异模式及供需矛盾。从构建乡村水域空间生态格局、乡村水域空间功能分区规划，以及乡村水域空间多情景预判3个方面，提出苏南水网乡村的适应性规划策略，并为水网乡村的生态实践提出新思路。     

Robust multivariate analysis for mixed-type data: Novel algorithm and its practical application in socio-economic research

We propose a novel method and algorithm for the analysis and clustering of mixed-type data using a hierarchical approach based on Forward Search. In our procedure, the identification of groups is based on the identification of similar trajectories and then linked to very intuitive two-dimensional maps. The proposed algorithm can use different measures for the calculation of distance in the case of mixed-type data, such as Gower’s metric and Related metric scaling. A key feature of our algorithm is its ability to discard redundant information from a given set of variables. The practical usefulness of the algorithm is illustrated through two applications of high relevance for empirical economic research. The first one focuses on comparing different indicators of environmental policy stringency in different countries. The second one applies our procedure to identify clusters of countries based on information regarding their institutional characteristics.     

Out-of-stock justifications and consumers’ behavioral outcomes– exploring the role of product type and sales level information in out-of-stock situations

The present study extends prior research on stockouts by examining how product-related attributes interact with OOS justifications to influence consumer responses to stockouts. Drawing from Out-of-stock (OOS) literature, this study investigates how perceived popularity, perceived uniqueness, negative affect, and behavioral outcomes are influenced by out-of-stock justifications, product type, and sales level. Two scenario-based experiments and two field studies are conducted in which the cause of the stockout, product type, and sales level are manipulated at different levels. The results of the studies provide the following primary insights- 1) Consumers infer popularity of the product when the product is OOS due to high demand or when the sales level is high 2) Consumers infer uniqueness of the product when the product is OOS due to short supply but not when sales level is low 3) As the perceived popularity of utilitarian products or the perceived uniqueness of hedonic products increases, consumers' propensity to switch stores to purchase the OOS products increases 4) Consumers’ intention to spread negative word of mouth decreases when the cause of OOS or a high sales level is specified. Retailers can influence behavioral outcomes by specifying the cause of stockout tailored according to the type of product, or by providing sales level information.     

试论土壤调查、土地类型与耕地评价兼论倪绍祥先生的土地评价思想

目的 以倪绍祥先生土地评价思想概括和我国土壤普查、土地类型述评为依据，探讨我国耕地评价工作完善路径和方向。方法 文章采用文献研究和对比分析方法。结果 （1）倪先生经过多年研究实践，形成以土壤调查为前提的，土地类型单元为基础，开展土地评价的系统思想。（2）我国土壤调查、土地类型工作中断，致使农用地分等定级、土地质量地球化学等工作缺乏扎实的数据基础，使得现有的耕地评价成果难以满足新时代耕地资源“三位一体”保护要求，也妨害国家对自然资源的科学管理。（3）国家生态文明建设、国土资源科技创新和自然资源管理机构职责整合等宏观背景，客观上要求将土地评价与土壤类型、土地类型相联系，夯实耕地评价的科学基础，创新耕地质量评价体系。（4）科学组织第三次土壤普查，服务于耕地评价实践，将土壤资源融入自然资源统一管理成为必然趋向。结论 倪绍祥先生有关土地评价思想，对于完善我国土地评价理论和方法体系，创新性开展第三次土地利用现状调查中的耕地质量调查专题，适应自然资源统一管理新形势具有重要借鉴价值。亟需科学组织新的土壤普查和土地类型调查研究，更新完善原有的土壤资源图和报告，深化中小尺度的土地类型调查研究，不仅深化人们对土地资源的客观认识，也为新的耕地质量评价提供客观、科学、高精度的数据基础提供可能。     

Optimal targeting of latent tourism demand segments

This paper identifies for the first time the optimal target markets employing the latent tourism demand expenditure, a novel concept in tourism literature. The study quantifies latent tourism demand between each pair of origin-destination through distinguishing by type of tourism and seasonality. It works with market shares that are estimated via a fractional regression model. Moreover, latent demand is clustered using a market segmentation approach based on a latent class regression. Finally, the optimal target markets are chosen depending on the expected latent tourism expenditure. The result has clear policy implications in terms of which markets are promoted, the optimal channels of communication and the maximum budget for each marketing campaign.     

Is the system reliability profitable for retailing and consumer service of a dynamical system under cross-price elasticity of demand?

Retailing strategy is one of the most crucial factors for industries. A proper retailing strategy can help to enhance consumer service and increase the industry's profit. An improved approach to retailing is suggested in this research to deliver superior customer service while maximizing profits in a dynamic system. The study analyzes a retailing strategy for a demand with cross-price elasticity upon the retail price. A product's cross-price elasticity and the system reliability are critical factors in retailing. Understanding the cross-price elasticity of demand between products helps retailers to make pricing decisions that maximize profits by maintaining demand. Imperfect products are produced due to an imperfect production system. The imperfect ones must be adjusted with some costs to make them perfect for better retailing. The system failure rate is crucial for retailing under cross-price elasticity of demand patterns. Production system reliability, cross-price elasticity of demand, and consumer service are all essential factors that can impact a company's success in the market. The production rate is considered time- and system failure rate-dependent. Contradictory to the literature, a dynamical system is proposed for improved retail management, which is solved using the Euler-Lagrange theory. Finally, one can achieve the expected maximum profit for this retail system with optimum selling prices for different products by reducing the system failure rate. Some numerical illustrations with graphical representations are provided to validate the current study. Numerical examples show that applying cross-price elasticity of demand for more than two identical products provides 35% more profit for the retail industry than a single type of product.     

险资股权投资的结构性改革研究*——基于险资投资的倒U型效应分析

保险资金作为重要的机构投资者能否发挥促进公司绩效提升的作用在已有研究和监管政策制定上都存在较大争议。本文以2005-2017年A股上市公司为研究样本，发现险资持股比例对上市公司绩效以及估值影响存在显著的倒U型曲线效应，相应机制研究表明险资持股通过显著影响两类代理成本的渠道发挥治理作用。在适度持股比例以下，险资增持能够降低被投资公司管理费用率和其他应收款占比，并提高资产周转率，从而降低两类代理成本；持股超过一定比例反而造成两类代理成本上升。险资持股比例变化对保险机构调研次数的影响则从公司治理参与角度印证了以上结论。对倒U型曲线效应的深入分析既有助于深化对机构投资者影响公司绩效的多重效应和机制的认识，同时为在金融机构层面落实金融供给侧结构性改革、增强险资服务实体经济能力提供参考。     

Cryptocurrencies and Cagan’s model of hyperinflation

The drivers of the prices of Bitcoin and Ethereum are studied within a framework based on Cagan’s model of hyperinflation. In the model, the prices of the cryptocurrencies are driven by stochastic adoption and velocity shocks as well as endogenous expectations of future prices. The model is estimated with data for prices, transaction volumes, and money supplies. A majority of price fluctuations in both currencies can be attributed to shocks in adoption, velocity shocks are much less important. The money demand sensitivity to expected price changes is estimated to be larger for Bitcoin than for Ethereum, and both have higher sensitivity than fiat currencies during episodes of hyperinflation.     

Advertisement policy for dual-channel within emissions-controlled flexible production system

Nowadays, industrial firms are very much careful to build a green environment by reducing carbon emissions. The government imposes some rules and regulations to provide a better eco-friendly environment. In this study, the cap-and-trade mechanism has been considered in a production model to control the carbon emissions rate. The manufacturers invest in advanced green technology to reduce per unit emissions. As online and offline selling is crucial to any industry for increasing customer demand, the manufacturers sell their products by dual-channel and advertise their products by online channel to make more popular of their products. Keeping these in mind, a sustainable flexible production model with single-type substitutable product production is considered here by imposing a cap-and-tax policy, investing in green technology, and advertising for products. This model is divided into two cases: with and without investment in green technology. The demand of each manufacturer depends upon an online selling price, an offline selling price, and an online advertisement of the product. A classical optimization technique helps to get the optimum strategies for the online selling price, offline selling price, advertisement investment, green technology, cycle time, and production rate. From the numerical study, it is proved that the industry gets 6.97% more profit in the case of green technology investment and the proposed study gives 5.74% more profit than the traditional production system. Sensitivity analysis and managerial insights are performed.