Subscribe to get access
Read more of this content when you subscribe today.
Read more of this content when you subscribe today.
Prof. Dr. Monica Dudian and Ana-Maria Sandica investigate the separation power of several machine learning techniques and compared them with the benchmark logistic regression using real data from 17520 private individuals of a Romanian commercial bank. The result of their research can be read in the book “Social Credit Rating“.
In order to capture the financial crisis effect they equally divided the data in two samples prior and posterior the crisis and we compared 13 models in terms of misclassification Type I and II Errors. As the models aim to catch best the patterns in the “default” profile of a consumer credit borrower, they split the variables in socio-demographic factors (Social Rating) and financial factors (Financial rating) and conclude that “default” profile prior crisis is captured better by the linear models while the patterns of the financial crisis are captured better by the non-linear models.
Monica Dudian and Ana-Maria Sandica found that the accuracy ratio gives the better results on decision trees and ensembles based on decision trees such as adaptive boosting methods (Financial Rating) and Random Forest (Credit Rating, Social Rating) irrespective of the sample choice.
The power of the model to classify the debtors using Social Rating, Financial Rating and the mix of these, the Credit Rating, depends on the trained data used. The Financial Rating’s champion model’s results are best on posterior crisis data, meaning that financial factors counted the most in detecting the patterns in “default” after the financial crisis. The order is not the same for Social Rating, where the best classification is obtained on prior crisis data meaning that classification considering the individual’s creditworthiness is more difficult on posterior crisis “default” patterns.
Prof. Dr. Monica Dudian is Professor of Economics at The Bucharest University of Economic Studies, where she received her PhD in Economics in 1999. She also held the position of Vice dean of the Faculty of Economics of The Bucharest University of Economic Studies, during 2001 – 2008. Her teaching is focused primarily on microeconomics and industrial organization. She manages research grants and performs research on country risk, credit risk, and industrial economics.
Dr. Ana-Maria Sandica has been developing credit risk models for more than 10 years. She started to study machine learning techniques during her master degree in Financial Econometrics (Dofin) and continued with completing a doctorate in the field of stochastic equilibrium models in Macroeconomy. Her thesis on postdoctoral research links the macroeconomic shock transmission mechanism in estimating the probability of bankruptcy for companies. She held a managerial role in model risk validation at a major German bank.
In the book “Social Credit Rating” you can read a lot about the nature and content of the social credit system, learn about governance, law and sustainability, as well as methods, models and functions. But what does that mean – for citizens as well as for companies? How can, how will Social Credit Rating change the world in the future?
Social Credit Rating is to be understood in the context of global digital transformation and geopolitically in the midst of the world-changing triad of “political systems”, “economic systems” and “digital systems”. As a digital system, it is crucial for Social Credit Rating which overarching values guide this technology in its interrelationships with business and politics and with which goal it is used.
In democracies, Social Credit Rating systems can help preserve citizens’ freedom. In autocracies they run the risk of becoming an instrument of everyday hostage that restricts individual freedom. In the economy, Social Credit Rating can support entrepreneurial assumption of responsibility, for example in the fight against climate change; in state capitalism, the fear is justified that Social Credit Rating mainly serves to build totalitarian power.
I recommend that you read the Contribution by Prof. Bernd Thomsen in the book “Social Credit Rating” by Springer.Dr. Oliver Everling, RATING EVIDENCE GmbH
So it shouldn’t be about discrediting Social Credit Rating, but about questioning the intentions of those responsible for digital rating systems. The current global crisis of meaning of the liberal democracies coincides with a shift in power in favor of repressive regimes. The current depression of capitalism coincides with a hype of state capitalism. Many people are just beginning to understand the extent of this. Social Credit Rating is a factor to be taken seriously not only in its transformative effect, but also for the western industrialized nations.
This article is about the credit reporting agency Creditsafe, the performance of the company and a concrete example of what a credit report from Creditsafe looks like in practice. Details of the offer are examined and discussed in detail. We carry out a fact check based on the official data from the Federal Gazette of the Federal Republic of Germany.
With more than 1,200 employees, including 120 in Germany, Creditsafe provides business information and financials to over 115,000 customers with over 365 million company data from 160 countries and from more than 8,000 sources. This is roughly an average of more than 300,000 company data per employee, who supports over 500,000 users for 450,000 decisions every day with the data provided by Creditsafe. Company data is updated five million times a day from local sources. This provides insight into the thousands of business events that occur every day. About 60% of reports available online contain payment details from suppliers.
Creditsafe is fortunate to have an extensive and ever growing database of up-to-date company information. As the database expands and increases the wealth of data Creditsafe holds, they must evaluate whether this data contains information that is indicative of company stability or future insolvency. Creditsafe must also re-validate whether previous indicators of future insolvency or stability remain true. In both cases, it is likely that adjustments to the scorecard will be needed to improve predictability.
To differentiate linguistically, Creditsafe calls its customers sometimes “partners” because customers are companies that in turn obtain information about other companies. Creditsafe partners can add companies from Belgium, Germany, Denmark, Finland, France, Great Britain, Ireland, Italy, Japan, Canada, Liechtenstein, Luxembourg, Netherlands, Norway, Austria, Sweden, Switzerland, Spain and USA to a list for which is monitored via email.
Because not all countries use a value from 1 to 100, Creditsafe is using a rating scale from A to E. This rating scale should make it easier to compare the credit risk of companies across national borders. A is the lowest risk, D is the highest, and E means that no assessment has been made.
Creditsafe accesses data on more than 49,000 active listed companies in over 165 countries around the world, as well as hard-to-find historical data on all non-trading companies involved in asset and real estate management:
The massive use of electronic data processing not only enables this high productivity unimaginable just a few decades ago, but also enables users to check their customers’ credit and financial data in real time. Unlike other credit bureaus, Creditsafe does not save historical reports, but checks all companies about which no information is available immediately. Whenever a report is not immediately available online for review, the company in question is re-examined to collect current, trustworthy information. Creditsafe wants to be able to serve research orders within five and a half days.
Integrating Creditsafe data with a customer relationship management system should be child’s play thanks to preconfigured apps for Salesforce, Sage, SugarCRM, SAP, Microsoft Dynamics, etc. Creditsafe apps should make manual entry and updating of customer data unnecessary and thus save time and resources. An option for the immediate creation and updating of data records is intended to correct and rely on the data.
The application programming interface makes the following systems available for Creditsafe:
Read more of this content when you subscribe today.
Telephone searches, stock indices, local agents, branches, official gazettes, payment histories, news, banks, directories, courts and registration authorities are among the sources of information (for researching registration addresses, see Civil Address).
Creditsafe also provides mass and individualized data in a file tailored to the ideas of the respective partner. With hundreds of selectable fields that support all aspects of the business, the content is designed to meet the specific requirements. Such files can be securely provided in a format of your choice, daily, weekly, monthly or quarterly.
Via a programming interface, Creditsafe enables integration into customer-specific Customer Relationship Management (CRM) systems and thus the consistent alignment of a company with its customers and the systematic design of customer relationship processes. The programming interface – Application Programming Interface, API for short – is the part of the program that is made available by a software system to other programs for connection to the system.
With Connect API, data should be integrated into the systems mentioned and users should have the opportunity to use Creditsafe business data in any required way. Direct real-time access to company data is intended to enable employees to make quick and informed decisions with data that the company can trust and that allow the development of new functions and automated processes.
If Creditsafe is connected to one of the systems mentioned, the following tasks should be possible:
Creditsafe supports customer and credit decisions in companies with creditworthiness information about private individuals, whose data comes from publicly accessible sources. This data is continuously supplemented by data from national and international partners and by manual research. Negative features include recorded in bankruptcy and debtor registers. Overview of all companies in which a natural person is a manager or in which they hold shares (see also Palturai).
The Creditsafe Data Cleaning Tool is a solution to improve data quality and is available in a total of 14 countries to correct duplicates, errors and outdated information, to identify inactive companies and data with a lot of information (such as company master data, balance sheet data, credit ratings, credit limits and contact information) ) enrich.
The Creditsafe Compliance Check supports the identification of potentially high-risk business relationships and their continuous monitoring (monitoring), for example in the case of current and previous sanctions against companies and private individuals, for the identification of Politically Exposed Persons (PEPs) and in the search for court judgments, negative reporting and bankruptcies .
What does a company search on the platform of “creditsafe.com” deliver? In the following you will see what creditsafe has to offer, what information to expect and how key performance indicators are calculated. Screenshots as of August 2020 guide you through the Creditsafe cockpit. Click on the screenshots in the text below to overlay images on the current page and see more details.
As the example of the music store shows, a professional assessment of creditworthiness cannot be replaced by looking at a few key figures. In the presentation of Creditsafe, the credit index and risk score reflect the good creditworthiness of the music store, which is based among other factors on high profitability, but not on a high equity ratio. Equity is created in the parent company, the results of the wholly-owned subsidiary are always transferred to the parent company, and any losses would be offset by the parent company. It is only through an overall view of all the relevant assessment criteria that Creditsafe can come to a plausible credit rating of the company’s creditworthiness.
Read more of this content when you subscribe today.
Bond purchases, like all investments, come with a certain amount of implied risk. The primary hazards of bond investing are the potential for non-payment and capital loss, caused by a decline in the instruments’ market value. Credit rating is the shortest profound and comprehensible profitability assessment of a given entity from viewpoint of its creditors. It gives an objective external opinion for the ability of a given debtor to serve his financial debts in a timely manner. Credit ratings are formed and disseminated based on established methodologies, models and criteria that apply to entities and securities that Credit Rating Agencies (CRAs) rate, including corporate finance issuers, financial institutions, insurance companies, public finance and sovereign entities as well as structured finance transactions.
The credit risk of issuers within a given jurisdiction is derived directly from the risk level of the State.The Government’s credit rating directly impacts other local bond issuers such as banks, public companies and state-owned enterprises. The sovereign rating usually serves as a ceiling for domestic enterprises’ own ratings, functioning as a reference point for pricing their bonds.
The reasons for the connection are as follows: A sovereign may impose currency controls on residents, effectively making the State a monopoly in the foreign currency revenues in the relevant territory. The country’s credit rating is indicative of macroeconomic conditions affecting a sovereign economy. This may influence foreign investors’ decision whether to operate within said economy. In some cases, the State guarantees corporate debt (especially that of government companies). While individual investors need to focus on their specific investment decisions, the time-consuming task of comparing sovereign risks and its impact all over the world is taken on by CRAs.
Credit Rating Agencies are creating value beyond data and information. At the heart of what makes them different is their people. They are powered by human insight and a collaborative culture that drives them forward – providing their clients and partners with the insight that has an impact on economies, businesses and livelihoods all over the world. Credit rating agencies play an important role in providing one source of information that aids market efficiency by reducing information costs, increasing the pool of potential borrowers, and reducing the imbalance of information that often exists between buyers and sellers of bonds. Their ratings are dedicated to improve the risk/reward decision-making capabilities of investors globally, while allowing issuers to access capital markets at premiums commensurate with their objectively assessed credit risk.
Credit risk is not only dependent on the organization of an issuer, but also dependent on an instrument’s individual attributes and many other factors. Government bonds denominated in local currency have a relatively low default risk, as sovereigns generally have the ability to print the money needed to repay creditors. For these securities, investors are exposed to a potential drop in the bonds’ value due to increased government debt issuances and inflation. These factors may erode a bonds’ real value. For bonds denominated in foreign currency there is a tangible risk of non-payment, as sovereigns are generally unable to print money to meet obligations.
Few investors have the time, resources or ability to frequently monitor issuer conduct and financial performance to derive the risk level associated with an investment.
The credit rating agencies perform these functions on behalf of investors. Credit Rating Agencies are supposed to use methodologies that are rigorous, systematic, continuous, dynamic and subject to constant validation, and should be completely independent and unbiased, politically and geographically. CRAs are obliged to work on the basis of strict internal controls as well as a robust and comprehensive system of governance. Their work includes monitoring issuers and their issues, reviewing issuer activities; publishing all relevant data to assess investment risk and assessing risk level according to a fixed proprietary scale.
Credit rating agencies take both an issuer’s ability to repay and the degree of commitment to debt repayment into account. With the expansion of the financial markets lending has become more complex and sophisticated. Credit rating is now vital to evaluating potential financial transactions and assisting in bond pricing. Credit rating reduces the dimension of uncertainty faced by potential investors, encouraging investment, and therefore declines in funding costs. In summary, credit rating is of vast importance, not only to the public sector, but to the economy as a whole.