银行信用评估模型效果的量化比较

信用评估模型能有效提高信用评估过程的科学性与结果的准确性.本文围绕主流信用评估模型在性能方面的差异化特征,基于德国信贷数据集、我国个人经营贷数据集与小微企业贷数据集,从六个模型性能评价维度对十二个代表性信用评估模型的拟合能力与泛化能力进行了深入研究.研究发现:(1)逻辑回归模型的总体性能最为优异,其次为判别分析、反向传播神经网络模型,其中逻辑回归模型与反向传播神经网络模型更适用于我国信贷场景;(2)基于无监督学习理论的自组织特征映射神经网络和k均值聚类模型,以及基于惰性学习理论的k最近邻模型的泛化能力较弱,表明各类有监督式主动学习模型更适用于解决信用评估问题;(3)模型理论与结构的复杂性并不必然能够使其在特定应用场景下获得较优的性能评价,结构简单、可解释性更强的模型往往稳健性更好.     

专利实施绩效的灰色关联评价研究——中原城市群实证

提高专利实施绩效是专利战略的重要环节之一。专利实施绩效主要包括社会效益和经济效益两个方面。社会效益包括新产品的市场覆盖率、企业的社会形象等;经济效益包括新产品的收益、投入产出比等。本论文将专利实施绩效评价指标选择为专利竞争力、专利经济效应、专利社会效应三个方面,具体包括7个指标。运用灰色关联分析方法进行评价的结果表明,郑州市由于其特殊的政治和经济优势,同样其专利实施绩效也处于最高的地位,而开封、漯河和济源由于各自不同的原因,其专利实施绩效还处于较低的水平。     

价值投资与行业轮动相结合的量化择股策略研究

把价值投资和行业轮动相结合进行量化择股,可以吸收两者的优点、避免各自的缺点。从实践的角度上看,这两者相结合,可以在投资的稳健程度和收益率之间找到更加有利的均衡。     

Economic benefits of adequate molecular monitoring in patients with chronic myelogenous leukemia

Objective:

Molecular monitoring of chronic myeloid leukemia (CML) has been associated with improved clinical outcomes during tyrosine kinase inhibitor therapy (TKI), yet recent studies have demonstrated its use is far below published guidelines. This study sought to determine frequencies of molecular monitoring and its impact on resource utilization and medical costs.

Methods:

A retrospective US claims administrative database (IMS LifeLink Health Plan Claims and Truven Health Analytics MarketScan databases, 11/2007–06/2012) was used to analyze the economic impact of qPCR testing in CML patients on first-line TKIs during the initial 12-months of treatment.

Results:

One thousand two hundred and five adult CML patients met the sample selection criteria. Among these, 41.0% had no qPCR tests, 31.9% had 1–2 tests, and 27.1% had 3–4 tests; 88.9% were initiated on imatinib; 47.7% were female. Patients in the 3–4 tests cohort incurred 44% (p?p?=?0.005) lower for the 3–4 tests cohort than the 0-tests cohort. Adjusted progression-related IP cost was $4132 (p?=?0.013) lower for the 3–4 tests cohort than the 0-tests cohort. Adjusted medical service cost was $5997 (p?=?0.049) lower for the 3–4 tests cohort than the 0-tests cohort.

Limitations:

Claims databases did not include information on the primary cause of hospitalizations.

Conclusions:

Among CML patients in two large claims databases, nearly three-quarters did not receive adequate molecular monitoring per published guidelines. Those who were more frequently monitored incurred lower medical service costs, with the majority of the difference in costs being related to disease progression. These findings underscore the clinical and economic values of molecular monitoring in CML.     

淮河流域安徽段工业化影响因素的空间计量分析

文章基于2000-2010年安徽淮河流域8个地市的统计数据,运用空间计量模型,对淮河流域工业化差异的影响因素进行实证分析。计量分析表明：淮河流域工业经济增长主要是靠资本要素推动的,但劳动要素也起到了重要的推动作用;工业全要素生产率对工业化水平差异的影响较大,工业化水平较高地区,其全要素生产率较高,工业化速度也较快。     

Essential concepts necessary to consider when evaluating the efficacy of quantitative easing

The economic impact from quantitative easing (QE) may be much less than assumed by the Federal Reserve. One focus is on the effectiveness of QE to stabilize a failing banking system, and the judgment here is largely positive. A second focus, especially in the US, is on evaluating subsequent rounds of QE that were implemented after the economy had resumed growth and after the banking sector had recapitalized and returned to profitability. For these subsequent rounds of QE, the reviews are decidedly mixed and heavily dependent on the assumptions embedded in the economic models used by the researchers. Researchers willing to assume that the US is a closed domestic economy tend to find a large impact on long-term interest rates from QE. If the US is part of a highly integrated global economy, a smaller effect is presumed. Then there is the more important and controversial evaluation of whether there is any impact on real GDP growth and job creation from QE once the economy is growing again, even if unemployment rates remain historically elevated. What one chooses to ignore or assume does not exist can be more important to the conclusions of QE evaluations than may meet the eye. Inappropriate assumptions can lead to poor decisions.     

Calibration of a nonlinear feedback option pricing model

We consider the option pricing model proposed by Mancino and Ogawa, where the implementation of dynamic hedging strategies has a feedback impact on the price process of the underlying asset. We present numerical results showing that the smile and skewness patterns of implied volatility can actually be reproduced as a consequence of dynamical hedging. The simulations are performed using a suitable semi-implicit finite difference method. Moreover, we perform a calibration of the nonlinear model to market data and we compare it with more popular models, such as the Black–Scholes formula, the Jump-Diffusion model and Heston's model. In judging the alternative models, we consider the following issues: (i) the consistency of the implied structural parameters with the times-series data; (ii) out-of-sample pricing; and (iii) parameter uniformity across different moneyness and maturity classes. Overall, nonlinear feedback due to hedging strategies can, at least in part, contribute to the explanation from a theoretical and quantitative point of view of the strong pricing biases of the Black–Scholes formula, although stochastic volatility effects are more important in this regard.     

Robust and adaptive algorithms for online portfolio selection

We present an online approach to portfolio selection. The motivation is within the context of algorithmic trading, which demands fast and recursive updates of portfolio allocations as new data arrives. In particular, we look at two online algorithms: Robust-Exponentially Weighted Least Squares (R-EWRLS) and a regularized Online minimum Variance algorithm (O-VAR). Our methods use simple ideas from signal processing and statistics, which are sometimes overlooked in the empirical financial literature. The two approaches are evaluated against benchmark allocation techniques using four real data sets. Our methods outperform the benchmark allocation techniques in these data sets in terms of both computational demand and financial performance.     

Rebuilding the limit order book: sequential Bayesian inference on hidden states

The limit order book of an exchange represents an information store of market participants’ future aims and for many traders the information held in this store is of interest. However, information loss occurs between orders being entered into the exchange and limit order book data being sent out. We present an online algorithm which carries out Bayesian inference to replace information lost at the level of the exchange server and apply our proof of concept algorithm to real historical data from some of the world’s most liquid futures contracts as traded on CME GLOBEX, EUREX and NYSE Liffe exchanges.     

发达国家量化宽松货币政策对中国国际收支影响的实证研究

发达国家量化宽松货币政策从实施到最后终结都经历了一个较长的过程,从目前来看,退出前景还不明朗。量化宽松货币政策主要通过贸易渠道和金融渠道对经济运行产生影响。通过建立向量自回归模型（VAR）,实证分析表明：欧美日量化宽松带来的货币供应量增加,短期内会对我国对其跨境收支和进出口产生正向冲击,且对跨境收支变化的解释能力较强;人民币实际有效汇率的变动会对我国对美日欧的进出口产生负向冲击,对我国对美日欧的跨境收入产生短期的正向冲击,对支出产生负向冲击。对此应进一步加快国内金融体制改革、转变对外贸易发展方式及完善人民币汇率形成机制等。