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.     

Price matching and product differentiation strategies considering showrooming

Showrooming, a phenomenon in which customers use brick-and-mortar stores to assess products and then purchase them from online retailers (o-retailers) for lower prices, is considered a great threat to traditional retailers (t-retailers). To combat showrooming, many t-retailers have executed price matching which enables customers to pay o-retailers' lower prices for the identical product. To avoid direct competition with t-retailers who execute price matching, many o-retailers have begun to sell differentiated products from t-retailers, which weakens the information advantage to customers from practicing showrooming. Motivated by these observations, we construct a duopoly game, where a t-retailer and an o-retailer sell products in a same category, to study the profitabilities of product differentiation and price matching in the context of showrooming. The results show that in the scenario without price matching, the o-retailer is likely to benefit from product differentiation only when the o-retailer's differentiated product is more popular with customers than the t-retailer's product. However, in the price matching scenario, the o-retailer also has the opportunity to benefit from product differentiation when the o-retailer's differentiated product is less popular with customers than the t-retailer's product, and product differentiation can be a win-win strategy for the two retailers under certain conditions. Considering the o-retailer's product differentiation decision, the t-retailer is only likely to execute price matching if the non-digital attributes of the product category sold by two retailers are not very obvious.     

粤港澳大湾区制造业集聚与区域创新

以2009—2020年粤港澳大湾区11个城市为研究对象，探讨制造业集聚与区域创新的关系。研究发现，制造业集聚显著提高区域创新水平，可通过提高企业竞争这一路径实现。进一步分析发现，金融业集聚对区域创新发展具有显著的正向关系，金融产业和制造业产融协同集聚显著提高区域创新水平。研究结果表明，制造业集聚加剧产业内部企业创新竞争，带动区域创新发展，且金融业在创新中起到积极的推动作用。指出应鼓励区域企业创新竞争，优化营商环境，为产业融合发展提供保障。     

Doing more and doing better are two different entities: Different patterns of family control and environmental performance

Family firms bear two types of agency costs, including type I and type II agency problems, in corporate environmental practices: (1) Outside executives at family firms hesitate to engage in environmental strategies, which can lead to drops in profits; (2) Controlling families employ opportunistically environmental management to achieve their interests. We argue that a primary cause for the agency problems lies on ineffective internal corporate governance at family firms, which can cause loss of managerial (or power) balance between outside executives and family executives. Our findings show that family firms with ownership and strategic control (FSC), which family executives and outside executives monitor and constrain each other, can achieve the highest environmental performance. Moreover, external controls, including product market competition and provincial environmental regulations, substitute effective internal control of FSC. The environmental performance premium of FSC is more prevalent when the production market competition is lower. Family firms with ownership, operational, and strategic control (FOSC) can achieve higher environmental performance within a province with more stringent environmental regulations.     

Does local government competition aggravate haze pollution? A new perspective of factor market distortion

Haze pollution has become a new threat to China's sustainable development, but it may be that local government behaviour can play an important role in the prevention and control of pollutants. A dynamic spatial autoregressive (SAR) model is used to study the relationship between local government competition and haze pollution. To further explore the indirect impact of factor market distortion on haze pollution and control potential endogeneity problems, a newly developed intermediary effect model that incorporates the characteristics of the generalized method of moments (GMM) is utilized to explore how factor market distortion indirectly affects haze pollution. The research results show that regional haze pollution in China is characterized by significant spatial correlation, and local government competition has a positive impact on haze pollution; that is, local government competition exacerbates haze pollution. In general, local government competition not only directly leads to an increase in haze pollution but also further intensifies it by distorting the local factor market, and the intermediary role of factor market distortion is approximately 7.04%. The results of the regional inspection found that competition among local governments in the eastern region did not lead to haze pollution, and distortion of the factor market did not exist as an intermediary effect. However, both direct and intermediary effects are significant in the central and western regions. Therefore, an official performance appraisal system that includes ecological constraints should be established to guide the benign transformation of local government competition, and an environmental management mechanism must be developed for joint prevention and control to reduce haze pollution. In addition, the free flow of factors and marketization are equally important.     

领导干部自然资源资产离任审计与企业绿色并购——来自中国重污染型上市公司的经验证据

基于2011~2017年我国A股重污染型上市公司经验数据，实证检验了领导干部自然资源资产离任审计对企业绿色并购行为的影响，研究发现：领导干部自然资源资产离任审计可显著促进辖区内企业实施绿色并购；而当地区市场竞争程度越高时，越会抑制企业在领导干部自然资源资产离任审计试点实施背景下的绿色并购扩张行为；进一步地，企业绿色并购会显著提高企业价值，且这一影响对并购后当年的企业价值影响最为显著；基于异质性分析方面，领导干部自然资源资产离任审计会约束不同产权性质企业的环境治理行为，促进其采取绿色并购，实施绿色发展；同时领导干部自然资源资产离任审计会更有利于东部地区企业实施绿色并购，而对中西部地区的企业影响不明显。     

20世纪50—60年代的中国财政学:一个传统的移入与退出

20世纪50—60年代既是新中国财政学初建时期,也见证了苏联财政学传统移入和退出的过程。就其理论和实践来源看,苏联财政学是苏联化的马克思主义、苏联特殊年代政治实践和计划经济体制等诸多因素的混合物。虽然它在发展和创新马克思主义财政理论方面作出了首创性的贡献,但其历史局限性也不可避免。在苏联财政学移植中国之时,其中一些负面特征也参与了新中国财政学的重建,并对其后中国财政学的发展起到了长久的羁绊作用。20世纪50年代后期以来,中国财政学“去苏联化”的目标未能完全实现,这一方面源于塑造苏联财政学的思维模式仍然在当时的中国财政学界起着支配作用;另一方面在那些影响财政学发展的主要因素上,当时的中苏两国极为雷同。吸取20世纪50年代中国移植苏联财政学的历史经验和教训,对当下中国合理借鉴域外学术资源、发展和创新马克思主义财政理论,有着重要的借鉴意义。     

M5 competition uncertainty: Overdispersion,distributional forecasting,GAMLSS, and beyond

The M5 competition uncertainty track aims for probabilistic forecasting of sales of thousands of Walmart retail goods. We show that the M5 competition data face strong overdispersion and sporadic demand, especially zero demand. We discuss modeling issues concerning adequate probabilistic forecasting of such count data processes. Unfortunately, the majority of popular prediction methods used in the M5 competition (e.g. lightgbm and xgboost GBMs) fail to address the data characteristics, due to the considered objective functions. Distributional forecasting provides a suitable modeling approach to overcome those problems. The GAMLSS framework allows for flexible probabilistic forecasting using low-dimensional distributions. We illustrate how the GAMLSS approach can be applied to M5 competition data by modeling the location and scale parameters of various distributions, e.g. the negative binomial distribution. Finally, we discuss software packages for distributional modeling and their drawbacks, like the R package gamlss with its package extensions, and (deep) distributional forecasting libraries such as TensorFlow Probability.     

Understanding machine learning-based forecasting methods: A decomposition framework and research opportunities

Machine learning (ML) methods are gaining popularity in the forecasting field, as they have shown strong empirical performance in the recent M4 and M5 competitions, as well as in several Kaggle competitions. However, understanding why and how these methods work well for forecasting is still at a very early stage, partly due to their complexity. In this paper, I present a framework for regression-based ML that provides researchers with a common language and abstraction to aid in their study. To demonstrate the utility of the framework, I show how it can be used to map and compare ML methods used in the M5 Uncertainty competition. I then describe how the framework can be used together with ablation testing to systematically study their performance. Lastly, I use the framework to provide an overview of the solution space in regression-based ML forecasting, identifying areas for further research.     

When and why do countries break their national fiscal rules?

This paper identifies determinants of compliance with various types of national numerical fiscal rules. Based on 51 fiscal rules in force in EU member states from 1995 to 2015, the analysis identifies determinants among specific rule characteristics and their fiscal frameworks, as well as their political, (socio-)economic and supranational environments. While the average compliance across all rules and countries is around 50%, compliance with rules constraining stock (rather than flow) variables, set out in coalitional agreements, as well as rules covering larger parts of general government finances is significantly higher. Furthermore, independent monitoring and enforcement bodies (issuing real-time alerts) turn out to be significantly associated with a higher probability of compliance. Several theories of the deficit bias of governments due to government fragmentation, decentralization and political budget cycles are also significant with regards to compliance with fiscal rules. However, neither the economic environment or business cycle, nor forecast errors (except for an unexpectedly higher primary balance) on average seem to play a significant role.