Granger causality detection in high-dimensional systems using feedforward neural networks

This paper proposes a novel methodology to detect Granger causality on average in vector autoregressive settings using feedforward neural networks. The approach accommodates unknown dependence structures between elements of high-dimensional multivariate time series with weak and strong persistence. To do this, we propose a two-stage procedure: first, we maximize the transfer of information between input and output variables in the network in order to obtain an optimal number of nodes in the intermediate hidden layers. Second, we apply a novel sparse double group lasso penalty function in order to identify the variables that have the predictive ability and, hence, indicate that Granger causality is present in the others. The penalty function inducing sparsity is applied to the weights that characterize the nodes of the neural network. We show the correct identification of these weights so as to increase sample sizes. We apply this method to the recently created Tobalaba network of renewable energy companies and show the increase in connectivity between companies after the creation of the network using Granger causality measures to map the connections.     

中国证监会2010年度证券行政处罚分析报告

为了从实证角度评估我国证券行政处罚的工作绩效,本文对中国证监会2010年的全部证券行政处罚案件(含市场禁入案件),根据不同的统计维度进行了专项统计分析。首先,对2010年证券案件处理方式、行政处罚具体类型、处罚对象数和处罚金额、年度收案结案比率等进行了总体的比较分析。其次,根据2010年证券行政处罚案件的数据信息,从违法行为、违法主体、处罚金额分布、深沪公司处罚数据对比、深市主板中小板处罚数据对比等维度展开专项统计分析。再次,分析了相关国家和地区2010年证券行政处罚案件的基本概况,并与我国相关数据进行了初步对比分析。从总体情况来看,我国证券执法的水平与我国资本市场在国际上所处的地位是相符合的。最后,本文对2010年被查处的内幕交易案件进行了专项统计分析,并与相关国家和地区证券监管机构查处内幕交易案件的情况进行了比较。总体上看,中国证监会内幕交易案件执法的力度和效率都取得了显著提高。     

试论信用卡恶意透支行为的入罪正当化

信用卡已成为百姓日常生活中常用的支付工具,由于其具有透支功能及使用便捷性,利用信用卡透支的持卡人也越来越多。2009年《信用卡刑事案件适用法律问题司法解释》出台后,信用卡透支刑事案件不断攀升,有必要就信用卡透支刑法规制进行探讨,以减少信用卡透支行为、保证刑罚的谦抑性、实现刑罚的效益。     

呆伯特专栏

正~~     

GAME CALL OPTIONS REVISITED

In this paper, having been inspired by the work of Kunita and Seko, we study the pricing of δ‐penalty game call options on a stock with a dividend payment. For the perpetual case, our result reveals that the optimal stopping region for the option seller depends crucially on the dividend rate d. More precisely, we show that when the penalty δ is small, there are two critical dividends 0 < d₁ < d₂ < ∞ such that the optimal stopping region for the option seller takes one of the following forms: (1) an interval if d < d₁; (2) a singleton if d∈ [d₁, d₂]; or (3) an empty set if d > d₂. When d∈ [d₁, d₂], the value function is not continuously differentiable at the optimal stopping boundary for the option seller, therefore our result in the perpetual case cannot be established by the free boundary approach with smooth‐fit conditions imposed on both free boundaries. For the finite time horizon case, the dependence of the optimal stopping region for the option seller on the time to maturity is exhibited; more precisely, when both δ and d are small, we show that there are two critical times 0 < T₁ < T₂ < T, such that the optimal stopping region for the option seller takes one of the following forms: (1) an interval if t < T₁; (2) a singleton if t∈ [T₁, T₂]; or (3) an empty set if t > T₂. In summary, for both the perpetual and the finite horizon cases, we characterize in terms of model parameters how the optimal stopping region for the option seller shrinks when the dividend rate d increases and the time to maturity decreases; these results complete the original work of Emmerling for the perpetual case and Kunita and Seko for the finite maturity case. In addition, for the finite time horizon case, we also extend the probabilistic method for the establishment of existence and regularity results of the classical American option pricing problem to the game option setting. Finally, we characterize the pair of optimal stopping boundaries for both the seller and the buyer as the unique pair of solutions to a couple of integral equations and provide numerical illustrations.     

住房抵押贷款提前还贷风险管理研究

从现代金融和风险管理角度看,住房抵押贷款提前还贷对商业银行是一种期权性风险,对其收取违约金并非国际惯例,也并不是有效的风险补偿方式。商业银行应适应市场竞争需要,接受风险转嫁并提供风险管理服务,运用风险定价技术在按揭交易价格中对提前还贷风险进行补偿。对于已承担的风险,商业银行应构建抵押贷款提前还贷的数据库,通过表内对;中和市场对冲,推出多样化的住房抵押贷款方式,积极推进住房抵押贷款证券化．从而最终增强银行的盈利来源和核心竞争力。     

惩罚性损害赔偿制度引入侵权责任法之合理性分析

在私法公法化的背景下,民事立法者在建构市场交易机制时,有时也会考虑到自治条件的不足,从而引进国家行政管制甚或刑事制裁,以加速自治条件的完善。对于我国《侵权责任法》中要不要引入惩罚性赔偿之规定学界一直存在较大争议,因为此种主张违背民事责任补偿性赔偿的基本定位而被贴上“民法刑法化”的标签。以“民刑责任关系”来审视惩罚性赔偿的立法取舍,惩罚性赔偿的存在和发展是《侵权责任法》在民法社会化思潮冲击下的功能修正。是公私法日渐交融趋势下的立法回应,无论在“民刑责任关系”的协调方面,还是社会的现实基础方面,都具有正当性依据。     

影响篮球裁判员临场判罚的主要因素研究

本研究对陕西省内篮球裁判水平进行调查分析,找出影响篮球裁判临场判罚的主要因素,在详细分析影响篮球裁判临场判罚的主要影响因素的基础上,提出了进一步提高篮球裁判水平的措施,为篮球裁判的培养提供理论参考。     

基于Logistic回归惩罚函数的企业财务危机预警

随着大数据时代的到来,企业的财务数据越来越复杂,在高维的财务数据中选出重要的影响因素,可以帮助企业人员对企业发生财务危机的可能性进行分析预测,降低企业的风险。研究企业财务危机的传统方法大多数是基于低维数据,而目前的财务数据变量众多。惩罚函数（penalty function）不仅能在高维数据的情况下进行稳定的变量选择,还能进行参数估计。采用基于Logistic回归惩罚函数模型研究企业财务危机预警问题,通过选取48个财务指标来进行建模和分析,找出影响企业财务危机的主要因素,并从预测精度、风险区分能力、变量选择这3个方面与传统方法进行对比,最终得到基于Logistic回归的惩罚函数方法更具有优越性。这对企业进行财务危机分析具有预警作用。