我国国际资本流动：直接投资 与非直接投资影响因素的比较研究

本文基于向量误差修正模型对1982-2010年期间我国直接投资类、间接投资类（含其他投资）、错误与遗漏及投资收益类三种类型国际资本流动的影响因素进行了实证研究。实证检验结果表明：在长期,我国三类国际资本流动与人民币对美元的实际汇率升贴水年率之间为负向变动关系,与中美利差、中美通胀之差、我国实际经济增长及人民币对美元的实际汇率预期之间为正向变动关系;在短期,三类国际资本流动与上述影响因素之间关系并非一致;实际经济增长是我国直接投资类国际资本流动的主要原因,人民币对美元的实际汇率预期是我国非直接投资国际资本流动的主要原因。     

我国风力发电项目投资风险评价——基于支持向量机模型

在分析我国风力发电项目投资风险并建立其评价指标体系的基础上,将支持向量机模型用于风力发电项目投资风险评价,全面衡量风力发电项目面临的经济风险、技术风险、政策风险等。支持向量机方法很好地解决了风力发电项目样本数据缺失、评价主观性问题。实证分析结果表明,利用支持向量机模型评价风力发电项目的投资风险,具有一定的适用性和准确性。     

外汇储备对我国物价水平的影响——基于协整检验与误差修正模型的分析

协整和格兰杰因果检验结果表明,我国外汇储备与物价水平存在协整关系,且外汇储备是物价水平的格兰杰原因,表明外汇储备增加将对通货膨胀形成压力。但从误差修正模型的检验结果看,我国外汇储备对物价水平的影响在短期内较为有限,其主要原因是我国央行短期内进行大量的外汇冲销操作。因此,我国需要采取有效的措施来缓解通胀压力,如加大央行公开市场业务操作、改革外汇管理体制、适当放宽汇率浮动幅度以及合理使用我国现有外汇储备等。     

我国虚拟经济与实体经济适度发展平衡区间：基于微分向量场方法

虚拟经济源于实体经济的再分配环节,随经济和社会的进步不断发生深刻的变化,对实体经济发展产生深刻的影响。虚拟经济与实体经济存在协调发展的平衡区间,以科学发展观为指导将二者发展保持在相对的平衡区间内,可以有效防范和降低金融风险。因此,在依据经济动力系统模型的基础上,提出了虚拟经济自增值的数理基础及对应的适度平衡区间。     

Combining wavelet decomposition with machine learning to forecast gold returns

This paper combines the discrete wavelet transform with support vector regression for forecasting gold-price dynamics. The advantages of this approach are investigated using a relatively small set of economic and financial predictors. I measure model performance by differentiating between a statistically-motivated out-of-sample forecasting exercise and an economically-motivated trading strategy. Disentangling the predictors with respect to their time and frequency domains leads to improved forecasting performance. The results are robust compared to alternative forecasting approaches. My findings on the relative importances of such wavelet decompositions suggest that the influences of short-term and long-term trends are not stable over the full evaluation period.     

A Novel Compact Cat Swarm Optimization Based on Differential Method

ABSTRACT

A compact cat swarm optimization scheme (cCSO) is proposed in this paper, which is designed to solve application domains plagued with limited memory and less-computation power, as a member of cat swarm optimization algorithms (CSO), it composes of two sub-modes, i.e., tracing and seeking modes, so it keeps the same search logic of CSO. On the other hand, cCSO inherits the main feature of compact algorithms, a normal probabilistic model is used to represent the population of solutions instead of processing an actual population, which ensures the cCSO to have the modest memory requirement. The updating vector for the probabilistic model provides a clear moving direction for cats in next step. A cat without historical position and velocity is applied in the algorithm. When the cat is in seeking mode, it employs a differential operator to update the cat’s position, which makes it possible for the cat to have multiple searching directions. Experimental results show that cCSO has pretty performance compared with respect to some population-based testing benchmarks. And it also shows superior performance in convergence rate to some compact optimization algorithms. The case study of gray image segmentation proves that it suits for solving the optimization problem by limited hardware.     

The relation between municipal and government bond yields in an era of unconventional monetary policy

In this paper, we investigate how the 5‐year Swedish municipal bond yield has been related to the corresponding yield on government bonds during the period that the Riksbank has conducted unconventional monetary policy in terms of bond purchases. Using daily Swedish data on bond yields from February 2015 to January 2018, we first conduct an event study to assess the short‐run effects of the Riksbank's bond‐purchase announcements. We then estimate bivariate vector autoregressive models to study the dynamic relationship between the yields. Results from the event study suggest that the accumulated short‐run effect of the Riksbank's announcements was to lower the government bond yield by approximately 40 to 50 basis points and municipal bond yields by 30 to 35 basis points. Our vector autoregressive analysis indicates—in line with the event study—that an unexpected decrease in the government bond yield initially increases the municipal bond‐yield spread. However, after approximately 4 weeks, the effect has been reversed and the municipal bond‐yield spread is lower than it was initially. By conducting this analysis, we contribute to the understanding of the transmission of unconventional monetary policy.     

Spatio-temporal probabilistic forecasting of wind power for multiple farms: A copula-based hybrid model

Accurate probabilistic forecasting of wind power output is critical to maximizing network integration of this clean energy source. There is a large literature on temporal modeling of wind power forecasting, but considerably less work combining spatial dependence into the forecasting framework. Through the careful consideration of the temporal modeling component, complemented by support vector regression of the temporal model residuals, this work demonstrates that a DVINE copula model most accurately represents the residual spatial dependence. Additionally, this work proposes a complete set of validation mechanisms for multi-h-step forecasts that, when considered together, comprehensively evaluate accuracy. The model and validation mechanisms are demonstrated in two case studies, totaling ten wind farms in the Texas electric grid. The proposed method outperforms baseline and competitive models, with an average Continuous Ranked Probability Score of less than 0.15 for individual farms, and an average Energy Score of less than 0.35 for multiple farms, over the 24-hour-ahead horizon. Results show the model’s ability to replicate the power output dynamics through calibrated and sharp predictive densities.     

基于改进Transformer模型的文本摘要生成方法

传统的文本摘要方法，如基于循环神经网络和Encoder-Decoder框架构建的摘要生成模型等，在生成文本摘要时存在并行能力不足或长期依赖的性能缺陷，以及文本摘要生成的准确率和流畅度的问题。对此，提出了一种动态词嵌入摘要生成方法。该方法基于改进的Transformer模型，在文本预处理阶段引入先验知识，将ELMo(Embeddings from Language Models)动态词向量作为训练文本的词表征，结合此词对应当句的文本句向量拼接生成输入文本矩阵，将文本矩阵输入到Encoder生成固定长度的文本向量表达，然后通过Decoder将此向量表达解码生成目标文本摘要。实验采用Rouge值作为摘要的评测指标，与其他方法进行的对比实验结果表明，所提方法所生成的文本摘要的准确率和流畅度更高。     

结合新型模糊支持向量机和证据理论的多传感器水质数据融合

在多传感器水质数据融合领域，证据理论是有效的数据融合方法之一，但基本概率分配一般不易确定，从而使数据融合能力难以有效发挥。支持向量机是统计学习理论之上的高级分类算法，具有普适性和全局优化等特点，但输出的基本概率分配有待进一步提高。提出了一种基于证据理论和新型模糊支持向量机相结合的数据融合方法，通过建立基于分类超平面距离的模糊隶属度，训练模糊支持向量机提高传统支持向量机的基本概率分配，并结合证据理论进行海河水质数据融合。通过证据理论分别结合支持向量机和模糊综合评价法与上述方法进行对比实验，经精度、平均绝对百分误差、均方根误差等指标验证，精度提高10.5%，表明所提方法是一种可靠的多传感器的水质融合方法，较其他方法具有更高的融合精度。