Detecting stock market manipulation via machine learning: Evidence from China Securities Regulatory Commission punishment cases

In this paper, we apply machine-learning techniques to construct detecting models of stock market manipulation. By combining manually collected China Securities Regulatory Commission punishment cases from 2014 to 2016 with financial information of listed companies, we construct a training set and a test set to compare the detecting ability of support vector machine (SVM) and logistic model. Considering imbalanced data, we further incorporate Borderline Synthetic Minority Oversampling Technique (Borderline SMOTE) to oversample minority class and then find that Borderline SMOTE–SVM performs better than SVM and benchmark model in detecting manipulation. To enhance detecting performance of the models, we innovatively introduce market sentiment indicators which are extracted from analyst rating reports, financial news, and Guba comments into our indicators set. The results indicate that the new indicators generate significant marginal increment to the model accuracy.     

The role of institutional investors in propagating the 2007 financial crisis in Southern Europe

The 2007 financial crisis has affected Southern European companies (Spanish, Portuguese, Italian and Greek) more than others. From a Minskyan bubble-burst cycle perspective (Minsky, 1986), we study the relation between institutional ownership structure and corporate risk-taking for a sample of non-financial listed companies from Spain, Portugal, Italy and Greece for the period 2001–2014. Our results suggest that the financial deregulation process, that lead to the financialization of the world economy before the 2007 financial crisis and the favourable macroeconomic scenario encouraged corporate risk-taking in those countries. We also find that the lack of effective control mechanisms provided an incentive for investment funds to assume a proactive role, encouraging companies to overinvest in risky projects.     

中国非金融企业金融化的影响因素分析

作为经济金融化微观层面的重要表现,非金融企业金融化现象日益凸显.以2001-2014年我国A股上市的非金融企业为研究对象,借助Eviews6.0软件,运用最小二乘法,从宏观和微观两个层面实证分析我国非金融企业金融化的影响因素.研究表明:企业的金融化程度随着其股东价值最大化观念的增强而加深,企业金融资产持有比例与其主营业务利润率呈U型关系,稳定的宏观经济环境会弱化企业的金融投资行为.     

Measuring financial soundness around the world: A machine learning approach

We use a fully data-driven approach and information provided by the IMF’s financial soundness indicators to measure the condition of a country’s financial system around the world. Given the nature of the measurement problem, we apply different versions of principal component analysis (PCA) to deal with the presence of strong cross-sectional and time dependence in the data due to unobserved common factors. Using this comprehensive sample and various statistical methods, we produce an alternative data-driven measure of financial soundness that provides policy makers and financial institutions with a monitoring and policy tool that is easy to implement and update. We validate our index by using alternative macroeconomic factors, confirming its predictive power. Our index captures important aspects of financial intermediation around the world.     

金融错配、非金融企业影子银行化与经济“脱实向虚”

当前,我国一些非金融企业通过直接或间接的方式从事影子银行业务。本文利用2004-2015年上市公司数据研究发现,金融错配程度的提高整体上会提高企业影子银行化规模,并且这种效应仅在金融深化程度较高、经济资源市场化配置程度偏低的地区显著;僵尸企业和盈利性较差的企业,分别受到“利润追逐”和“投资替代”机制的影响,金融错配对其影子银行化趋势的正向作用更为明显。机制检验发现,金融错配水平的上升通过提高融资约束程度从而降低企业实体投资水平,这种效应在资产专用性较强的企业中更为明显;金融错配主要通过融资约束程度和实体投资规模,而非资本回报率渠道作用于企业影子银行化行为。本文研究对于提高信贷资源配置效率,防范经济“脱实向虚”具有较强的政策意义。     

金融错配、非金融企业影子银行化与经济“脱实向虚”

当前,我国一些非金融企业通过直接或间接的方式从事影子银行业务。本文利用2004-2015年上市公司数据研究发现,金融错配程度的提高整体上会提高企业影子银行化规模,并且这种效应仅在金融深化程度较高、经济资源市场化配置程度偏低的地区显著;僵尸企业和盈利性较差的企业,分别受到“利润追逐”和“投资替代”机制的影响,金融错配对其影子银行化趋势的正向作用更为明显。机制检验发现,金融错配水平的上升通过提高融资约束程度从而降低企业实体投资水平,这种效应在资产专用性较强的企业中更为明显;金融错配主要通过融资约束程度和实体投资规模,而非资本回报率渠道作用于企业影子银行化行为。本文研究对于提高信贷资源配置效率,防范经济“脱实向虚”具有较强的政策意义。     

BANKRUPTCY DISCRIMINATION WITH REAL VARIABLES

This paper reconsiders the accepted usage of nondeflated financial ratios in statistical models to differentiate between failed and nonfailed firms. Non-deflated ratios are hypothesized to inadequately reflect inter-temporal macroeconomic fluctuations that affect the ability of firm's to survive. Using a sample of 124 oil and gas companies between the period 1982–1988, the going concern assumption is evaluated with statistical logit models using either nondeflated or deflated financial ratios. Deflated company ratios are created by transforming data with price indices or by creating market value ratios. Empirical results suggest that a superior bankruptcy early warning model is developed for the oil and gas industry by creating real financial and reserve ratios and by introducing external factors, such as oil prices, interest rates and accounting method, as independent predictors. Overall classification accuracy is approximately 95 percent.     

Features selection,data mining and finacial risk classification: a comparative study

The aim of this paper is to compare several predictive models that combine features selection techniques with data mining classifiers in the context of credit risk assessment in terms of accuracy, sensitivity and specificity statistics. The t‐statistic, Battacharrayia statistic, the area between the receiver operating characteristic, Wilcoxon statistic, relative entropy, and genetic algorithms were used for the features selection task. The selected features are used to train the support vector machine (SVM) classifier, backpropagation neural network, radial basis function neural network, linear discriminant analysis and naive Bayes classifier. Results from three datasets using a 10‐fold cross‐validation technique showed that the SVM provides the best accuracy under all features selections techniques adopted in the study for all three datasets. Therefore, the SVM is an attractive classifier to be used in real applications for bankruptcy prediction in corporate finance and financial risk management in financial institutions. In addition, we found that our best results are superior to earlier studies on the same datasets.     

Analysing the financial strength of Tunisia: An approach to estimate an index of financial safety

This paper analyses the strength of the financial system of Tunisia through the construction of an Index of Financial Safety (IFS). Over the period 2000Q1–2014Q3, the IFS is built using a wide range of financial and macroeconomic indicators. The empirical results show that it can capture the disturbances in Tunisian financial system with sufficient accuracy.     

The impact of corporate governance on financial performance of Indian and GCC listed firms: An empirical investigation

Corporate governance plays a vital role in creating a corporate culture of consciousness, transparency, and openness. In this context, this paper provides a brief view about the background of corporate governance mechanisms in India and Gulf Corporation Council (GCC) countries, corporate legal system and monitoring policies laid down by Indian and GCC governments. Furthermore, it analyzes the impact of corporate governance mechanisms on the financial performance of Indian and GCC listed firms. The study uses a sample that consists of 53 non-financial listed companies from India and 53 non-financial listed companies from GCC countries for the period 2009–2016. Results revealed that board accountability (BA) and audit committee (AC) have an insignificant impact on firms' performance measured by ROE and Tobin’s Q. Similarly, transparency and disclosure (TD) have an insignificant negative impact on firms' performance measured by Tobin’s Q. Moreover, the country dummy results show that Indian firms are performing better than Gulf countries ones in terms of corporate governance practices and financial performance. The current study is considered as a battery for further research and studies particularly in India & GCC listed firms in the context of corporate governance and financial performance.     

Predicting banking distress in the EMEAP economies

This study develops a panel probit model to identify the leading indicators of banking distress and to estimate the banking distress probability for EMEAP economies. Macroeconomic fundamentals, currency crisis vulnerability, credit risks of banks and non-financial companies, asset price gaps, credit growth, and the occurrence of distress in other economies are found to be important leading indicators. The model is applied to stress test the Hong Kong banking sector. Simulation results suggest that compared with the period before the Asian financial crisis, the banking sector is currently more capable of withstanding shocks similar to those that occurred during the crisis.     

金融资产投资、杠杆率与企业风险承担——基于非金融企业的视角

本文以2007~2018年我国A股非金融上市公司为研究样本,运用动态面板系统广义矩估计法,研究杠杆率在金融资产投资与企业风险承担之间的中介效应影响,分析金融资产投资、杠杆率、企业风险承担三者之间的传导链条。研究发现:杠杆率在金融资产投资与企业风险承担水平之间发挥了部分中介效应;金融资产投资增加会直接导致企业风险承担水平上升,同时也会通过提高杠杆率间接地提升企业风险承担水平。本研究丰富了实体企业金融投资后果的相关文献,为实体企业的投资决策以及风险管理提供了参考,也为监管部门去杠杆防风险提供了经验证据。     

Rating or no rating? That is the question: an empirical examination of UK companies

The aim of this paper is to examine the main determinants of the rating likelihood of UK companies. We use a binary probit specification to model the main drivers of a firm's propensity to be rated. Using a sample of 245 non-financial UK companies over the period 1995–2006, representing up to 2872 firm years, the study establishes important differences in the financial profiles of rated and non-rated firms. The results of the rating likelihood models indicate that the decision to obtain a rating is driven by a company's financial risk, solvency, default risk, public debt issuance, R&D, and institutional ownership, thus identifying a wider range of determinants and extending the current literature. The study also finds that the rating decision can be modelled by means of a contemporaneous or predictive specification without any loss of efficiency or classification accuracy. This offers support to the argument that the rating process is fundamentally forward-looking.     

宏观经济信息与金融市场关联性——来自混频动态条件相关系数模型的证据

宏观经济信息是金融市场之间相互传递的重要信息内容,有效利用宏观经济信息是否有助于更好地理解金融市场关联性？为此,本文运用混频动态条件相关系数(DCC-MIDAS)模型分析了我国四个重要金融市场之间的动态相关性如何受到纳入的宏观经济信息的影响。结果发现:(1)工业增加值和货币供应量M2负向影响金融市场关联性,经济政策不确定性和通货膨胀水平反之。前三者是影响金融市场关联性较为重要的因素,而通货膨胀的重要性相对较低;(2)宏观经济信息作为市场关联性的长期成分相较基于市场信息的模型可以获得至少1.45%的效率提升。(3)工业增加值和通货膨胀对金融市场关联性的影响较为稳健,货币供应量M2和经济政策不确定性的影响表现出周期性特征。经济上行阶段工业增加值、货币政策信息带来的效率提升更为明显,经济下行阶段政策不确定性相对重要。本文研究结论对于加强金融监管协调和防范金融市场风险共振具有参考价值和指导意义。     

Japan’s banking crisis: An event-study perspective

We calculate abnormal stock returns for Japanese non-financial companies around major events associated with the banking crisis (1995–2000), and find that not all companies were equally sensitive to the malaise of the banking sector: the most affected were small, leveraged, low-tech companies with low credit ratings and low market to book ratios. This is consistent with “credit crunch” theories (companies with limited access to financial markets are sensitive to changes in bank lending) and with claims that innovation is rarely financed by bank debt. We do not find much evidence on the alleged misallocation of loans to support ailing bank clients.     

Using Financial and Macroeconomic Indicators to Forecast Sales of Large Development and Construction Firms

Sales forecasting is a pivotal component of a corporation’s planning and control activities. Despite the panoply of approaches to sales forecasting, relatively few published studies in forecasting address firm-specific sales forecasting model development for the construction industry. While there is evidence that events in the macroeconomy significantly affect the construction market, most published studies on construction sales forecasts using S-curve models are unable to account for the economic climate. This study proposes an approach that employs financial and macroeconomic indicators to forecast sales of large development and construction corporations. First, by using data for 37 large development and construction firms listed on the construction sector of the Taiwan Stock Exchange between 1997 and 2006, hypothesis tests uncover useful relationships between firm sales and financial and macroeconomic indicators. Second, based on these relationships, a two-stage mathematical modeling procedure is used to develop firm-specific sales forecasting models for three of the sample firms. Finally, out-of-sample forecasting accuracy is evaluated using Theil’s U-statistic and mean absolute percentage error (MAPE).     

我国商业银行中小企业信贷风险评估体系的构建

开展中小企业贷款业务是商业银行优化信贷资产结构的重要措施,快速、准确评估其信贷风险是商业银行亟须解决的技术问题.经过长期实地调研,本文建立了适用于我国的中小企业信贷风险评估体系,其中,所建非财务指标体系,从行业环境、企业经营管理水平、经营者经验与素质、信用品质四方面进行评估;财务指标体系包括现金流流动负债比、净资产总资产比、息税前利润流动负债比、总资产周转速度、流动比率、现金流贷款比六个指标.以Logit统计回归模型为基础建立的评估模型,在分别评估非财务指标信息和财务指标信息后,加权相加两方面结果得到综合评估结果.实证检验证明,该评估体系的评估正确率达到95%以上.