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.     

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.     

Does computer penetration increase farmers’ income? An empirical study from China

The diffusion and adoption of modern information technology provide new chance for China to close urban-rural income gap. This paper uses China's provincial panel data from 2002 to 2013 to investigate the effect of computer penetration on rural residents' income. A public program aiming to connect every village with broadband Internet and other rural facilities provides plausibly exogenous variation in rural residents' availability and adoption of the broadband Internet, which is used to explore the instrument variable for rural computer penetration. The results show that rural computer penetration tends to increase rural residents' income over time, but the average effect remains limited. The dynamic panel threshold effects model, which allows for both the threshold variable and other covariates to be endogenous, is further used to explore the constraints of the income-increase effect of rural computer penetration. It shows that the effect is at least doubled over the average effect estimated from instrument variables method, once the digital divide causes are removed. Our findings have important implications for the government to increase rural residents' income and reduce urban-rural income gap by encouraging rural computer usage and removing the digital divide.     

The provision of long-term credit and firm growth in developing countries

Do small and young firms benefit from an increase in the provision of long-term loans? By combining firm-level data from 62 countries (over the period 2006–2016) with a new database on short-term and long-term credit provided to the private sector, this article shows a higher provision of long-term credit does not stimulate growth of small and young firms. On the contrary, an increase in the availability of short-term credit spurs firm growth. The main explanation of this (counter-intuitive) result is the differential impact of short-term and long-term credit provision on small and young firms’ access to credit. Young and small firms are able to take advantage of an increase of short-term loans, which allow them to switch from informal finance to bank loans. However, a higher level of long-term credit does not alleviate credit constraints faced by opaque firms because these funds are allocated towards transparent borrowers.     

Bertrand versus Cournot competition in a downstream mixed oligopoly with foreign ownership

Focusing on foreign ownership in the private firm, we examine the Cournot-Bertrand comparison in a mixed oligopolistic market with vertical market structure. We have found that if public and private firms were charged with uniform price for their inputs, then Cournot-Bertrand ranking in market outcomes confirms those obtained by Ghosh and Mitra (2010). This implies that under uniform pricing in the upstream sector, the vertical market structure does not have substantial influences on Cournot-Bertrand ranking. However, if discriminatory pricing is adopted, firm's profits, output, and social welfare are often reversed to those obtained from uniform pricing in the upstream sector. Given the closeness of products, if the share of foreign ownership is sufficiently low, social welfare in Cournot competition can exceed that of Bertrand competition, contrasting with the standard welfare ranking that Bertrand welfare is strictly higher than Cournot. This implies that Cournot competition can be more socially desirable than Bertrand in mixed oligopoly with vertical market structure if discriminatory pricing scheme is adopted by foreign upstream monopolists.     

Optimal privatization policy with asymmetry among private firms

We revisit the relationship between the optimal privatization policy and market competition indexes such as the Hirschman–Herfindahl index. It is affected by the number of the firms and asymmetry among the sizes of the firms; the smaller the number of firms and the more asymmetry among firms, the higher the market concentration index. The literature on mixed oligopolies suggested that the optimal degree of privatization increases with the number of private firms, and thus, decreases with the market competition index, assuming that all private firms are homogeneous. We investigate how asymmetry among private firms affects the optimal degree of privatization. We propose the simplest and natural model formulation to discuss asymmetry among private firms. We find that the optimal degree of privatization is either nonmonotone or monotonically increasing, and thus never monotonically decreasing, in asymmetry among private firms.     

Neighbors and friends: How do European political parties respond to globalization?

This paper explores the relationship between globalization and party positions accounting for potential differences between left- and right-wing parties. The analysis is based on a panel model of 36 political parties in 18 Western European countries between 1970 and 2015. We find that right-wing parties move leftward in response to globalization, while left-wing parties do not alter their position. Additionally, we find that ideological party positions are affected by foreign parties’ positions of the same ideological bloc. These findings indicate that there is a convergence towards the left of the political spectrum due to right-wing party moderation.     

Interenterprise Credit and Adjustment during Financial Crises: The Role of Firm Size

Small and medium‐sized enterprises (SMEs) suffered a sharp contraction in their borrowing from banks during the Great Recession. Analyzing a large firm‐level database for European countries, the paper shows that trade credit amplified the liquidity squeeze on SMEs, with adverse effects on their real activity. SMEs sharply increased their net trade credit and thus transferred financial resources to larger firms. Given the large weight of SMEs in the economy of European countries, the liquidity squeeze of SMEs likely contributed to the depth of the output fall and the slow recovery in Europe during the Great Recession.     

一种基于SIR结构的三通带带通滤波器

应用双指耦合结构和枝节加载谐振器（Stub-loaded Resonator，SLR）实现了一款基于阶梯阻抗谐振器（Stepped Impedance Resonator，SIR）的滤波器。该滤波器具有3个通带，带外抑制较好，工作频段提高。通过调整阻抗比可调节第二、三通带的谐振频率；SLR结构能够增加通带数量；SLR结构和双指耦合结构均能改善滤波器的S参数。HFSS软件仿真表明，3个通带的中心频率分别为3.5 GHz、6.6 GHz、9.2 GHz，对应的分数带宽分别为5.7%、3%、2%，S11分别为-18 dB、-22 dB、-24 dB，通带内的S21分别为-1.8 dB、-1 dB、-1 dB。电路的测量结果与仿真结果较为吻合。该滤波器在5G通信的低频段具有应用前景。     

Diagnosing a healthcare cybersecurity crisis: The impact of IoMT advancements and 5G

Internet of Medical Things (IoMT) technology remains in early stages of adoption, but advancements and breakthroughs are quickly moving this process forward. There is a critical need for cybersecurity to be a priority in the development of these new tools, alongside design and utility. Given the rapid pace and potential magnitude of the coming advancements in IoMT, if privacy and security risks are neglected, a significant crisis could emerge in the form of more frequent cybersecurity breaches. This article examines the market opportunities and risks associated with IoMT and outlines a plan for proactively mitigating concerns and providing a platform to foster growth, to modify attitudes and behaviors, and to continue to build consumer confidence in the overall health system without sacrificing security.