Forecasting US bond default ratings allowing for previous and initial state dependence in an ordered probit model

In this paper we investigate the ability of a number of different ordered probit models to predict ratings based on firm-specific data on business and financial risks. We investigate models which are based on momentum, drift and ageing, and compare them with alternatives which take the initial rating of the firm and its previous actual rating into account. Using data on US bond issuing firms, as rated by Fitch, over the years 2000 to 2007, we compare the performances of these models for predicting the ratings both in-sample and out-of-sample using root mean squared errors, Diebold-Mariano tests of forecast performance and contingency tables. We conclude that both initial and previous states have a substantial influence on rating prediction.     

Is there valuable private information in credit ratings?

Credit rating agencies (CRAs) contend their ratings contain a quantitative assessment based on hard information, and a qualitative adjustment based on private information. We study if the qualitative portion of ratings, generated with the companies’ own private information, contains valuable information for equity investors. We generate predicted ratings based on hard information alone and form portfolios of stocks based on the difference between observed and predicted ratings. Over a sample from 1998 to 2018, we find that stock portfolios formed on the basis of private information generate 2% to 4% in annual risk-adjusted returns. We also find that companies with positive private information have better future accounting performance. Our results suggest that CRAs bring valuable information to the market and investors could benefit from it.     

关于构建我国保险信用评级制度的思考

保险信用评级制度是为市场参与者提供服务的一种机制,虽然保险信用评价制度已有近百年的历史,但是在中国等发展中国家,信用评级机构还比较少,信用评级制度急需完善。文中从各个方面讨论和思考了我国保险信用评级制度的构建问题,对我国保险信用评级制度起了一定的推动作用。     

对我国金融信用法制体系建设问题的思考

市场经济条件下,法制是正常的金融信用关系得以维系的重要保障,金融法制建设是完善金融信用体系的重要内容。近年来,我国金融信用法制建设虽有所进展,但与现实的金融经营活动相比仍显滞后及不完善。加快金融信用法制体系建设已成为当务之急。     

小额贷款公司存在的问题及建议——对郎溪银达小额贷款公司试点进展情况的调查

本文通过对郎溪银达小额贷款公司试点进展情况的调查,以银达小额贷款公司业务开展情况,分析了小额贷款公司存在的人员素质和贷款技术、资本实力和风险集中、小额贷款经营和监管等方面的问题,并提出了一些相应的解决方法,希望对小额贷款公司存在的问题提供一些建议。     

美国次贷危机对我国住房金融的启示

本文从美国次贷危机的形成着手分析其产生的背景,剖析其风险积累过程,进而阐述该危机对美国经济乃至世界经济和中国的影响,并结合日本金融泡沫破裂的教训,总结对我国住房金融发展的启示。     

Post-script—Retail forecasting: Research and practice

This note updates the 2019 review article “Retail forecasting: Research and practice” in the context of the COVID-19 pandemic and the substantial new research on machine-learning algorithms, when applied to retail. It offers new conclusions and challenges for both research and practice in retail demand forecasting.     

小额贷款公司的问题及出路

小额贷款公司是金融创新的成果,其短期、高效的运作特点为我国农村金融市场注入活力,进一步促进“三农”发展。文章以小额贷款公司为主,深入分析其产生的背景,以及存在的问题,积极探索突破制约小额贷款公司发展瓶颈的优化路径,为小额贷款公司的发展提供理论和实践依据。     

中小企业信贷融资约束及其对策研究——从制度性约束和信息不对称视角考察

中小企业迅速发展已成为我国经济社会发展的重要推动力。然而,中小企业发展的最大障碍问题仍然是融资难。本文借助于金融缺口理论考察中小企业信贷约束困境,并从制度性约束和信息不对称视角,深层分析了信贷约束的原因,为化解我国中小企业信贷约束,应从融资制度安排上进行重点设计。     

How to “improve” prediction using behavior modification

Many internet platforms that collect behavioral big data use it to predict user behavior for internal purposes and for their business customers (e.g., advertisers, insurers, security forces, governments, political consulting firms) who utilize the predictions for personalization, targeting, and other decision-making. Improving predictive accuracy is therefore extremely valuable. Data science researchers design algorithms, models, and approaches to improve prediction. Prediction is also improved with larger and richer data. Beyond improving algorithms and data, platforms can stealthily achieve better prediction accuracy by pushing users’ behaviors towards their predicted values, using behavior modification techniques, thereby demonstrating more certain predictions. Such apparent “improved” prediction can result from employing reinforcement learning algorithms that combine prediction and behavior modification. This strategy is absent from the machine learning and statistics literature. Investigating its properties requires integrating causal with predictive notation. To this end, we incorporate Pearl’s causal operator into the predictive vocabulary. We then decompose the expected prediction error given behavior modification and identify the components impacting predictive power. Our derivation elucidates implications of such behavior modification to data scientists, platforms, their customers, and the humans whose behavior is manipulated. Behavior modification can make users’ behavior more predictable and even more homogeneous; yet this apparent predictability might not generalize when business customers use predictions in practice. Outcomes pushed towards their predictions can be at odds with customers’ intentions, and harmful to manipulated users.     

信用评估中的特征选择方法研究

特征（变量）选择是信用评估中常用的一种数据降维技术,然而传统的基于相关性的特征选择方法（CFS）在计算变量间相关系数时,本质上是一种线性分析方法,无法有效处理非线性关系的数据,导致不能准确估计变量间相关性的大小。本文在分析CFS方法的基础上,引入Gebelein最大相关系数（GMC）,提出了一种非线性相关性特征选择方法——基于Gebelein最大相关性特征选择方法（GCFS）。在此基础上,结合支持向量机（SVM）技术,构建了GCFS SVM评估模型。该模型能有效地识别变量间的非线性相关关系,更真实估计变量间相关系数大小,从而筛选出最优变量子集,最终提高模型评估预测能力。为验证本文所提方法的效果,通过对两个公开的信用数据集的实证研究,结果表明：与其他方法相比,本文提出的GCFS方法能显著改善信用评估模型预测性能,提高模型判别能力,本研究成果也为信用评估模型的构建提供了一种新的思路和有益的参考。     

互联网理财产品利弊分析

面对"互联网理财产品"的异常火爆,专家褒贬不一,传统金融业也在不断调整自己的营销战略应对金融体系的变化,投资人一边在担心着余额宝的安全性,一边又在不断跟跑着不断变出新花样的理财产品。如何认识互联网理财产品,其对整个金融体系的利与弊如何,本文进行粗浅的分析。     

我国汽车金融公司与商业银行在汽车消费市场的SWOT对比分析

"SWOT分析法"是一种综合考虑企业内部因素与外部因素,用系统的思想,对企业进行评价,使得制定企业战略计划更加具有科学性的方法。通过对汽车金融公司与商业银行在汽车消费市场上的SWOT对比分析,总结出汽车金融公司与商业银行各有的优势、劣势、机会和威胁,提出了汽车金融公司与商业银行合作下的互补性优势,为汽车消费信贷市场中汽车金融公司与商业银行的合作提供了理论上的借鉴。     

政策冲击、投资者信息与平台竞争力——来自网络借贷市场经验证据

基于410家P2P网络借贷平台的运营数据,以2017年前3次出台的监管政策为切入点,采用面板回归、门槛回归、分位数回归、系统GMM和差分GMM模型探究了政策不确定性背景下监管政策出台对投资者信心、平台竞争力以及二者之间内在关系的影响。结果表明：政策异质性对投资者和平台竞争力以及二者之间内在关系的影响具有显著的差异化特征。进一步研究发现：面对行业政策不确定风险,新投资人更加敏感,老投资人更加稳健,二者都具有较强流动性偏好;行业监管政策对平台竞争力的提升效果显著;平台竞争力与投资信心之间有双向因果关系,在不同政策冲击下,老投资者投资信心与平台竞争力双向因果关系更加稳健。     

Are credit rating agencies regionally biased?

We investigate claims of regional bias in the sovereign credit ratings given by the rating agencies Fitch, Moody’s and Standard & Poor’s by considering a wide range of macroeconomic, financial, institutional, regional and geopolitical indicators for 99 countries categorized into eight regions plus the United States. Empirical results based on seemingly unrelated regressions indicate a strong home country bias towards the United States, while there seem to be no special biases against individual groups of countries. We also demonstrate how modeling errors such as omitted variables can increase dispersion in the estimated regional effects, causing agencies to appear biased.