Ken School Risk & Investment Studies

Which borrowers will default, or become delinquent, or prepay? Those are questions that lenders wish they had a crystal ball to answer, and their hopes are being raised by the advent of artificial intelligence.

AI today, in the form of machine learning, is not perfectly predictive, but it is a lot closer than it was. It's in the laboratory – or, more specifically, the accelerator – of Synechron. The New York-based consulting firm announced on October 22 the launch of its AI Data Science Accelerators, and within it a project applying AI to credit risk.

Synechron head of data science Robert Huntsman said that powerful distributed computing software, especially the open-source variety, has enabled significant advances in machine learning and data analytics. AI Data Science Accelerators is the fifth such program launched through the firm's Financial Innovation Labs (FinLabs) innovation hub, operating in 11 locations worldwide.

Robert Huntsman Headshot
Clients are getting “much more insight into their credit portfolios than they have had historically,” says Synechron's Robert Huntsman.
The data science accelerators include AI Data Science, which ingests large volumes of structured and unstructured data, automates the generation of personalized buy- and sell-side research reports, alerts wealth managers to critical events, and identifies factors driving customer complaints. The credit risk component, according to Synechron, “empowers banks to manage their credit portfolios proactively, enabling users to drill down into the factors driving likely credit events and to proactively manage individual risks ranked by probability of incurring a specific credit event.”

Prescriptive Management

Synechron's credit solution cannot be used to underwrite loans. Huntsman said that lenders offering mortgage, credit card and/or auto loans have long used logistic-regression models for underwriting, and regulators have grown comfortable with that approach. The machine learning methods known as random forest, neural networks and clustering have yet to attain that regulatory status, but they can be used to manage credit prescriptively.

“A bank with an existing loan portfolio wants to know who is going to default or become delinquent on loans, and who will prepay them. These are the biggest challenges faced by our clients,” Huntsman said.

The accelerator program is built around massive amounts of data. In the case of mortgage loans, AI Data Science analyzes data on more than 2.1 million loans that Fannie Mae provides on its website. The data is anonymized, but it comprises 55 attributes and the entire payment history for each loan. Synechron's separate models for delinquencies, defaults and prepayments also incorporate macro-economic data, such as state unemployment rates and GDP growth.

High Accuracy

Huntsman said the models predict 95% of prepayments, and 80% to 85% of defaults and delinquencies.

“These numbers are high relative to what we've seen with traditional credit-rating models, where accuracy of 70% is considered very good,” he said. “We've seen that using machine learning provides clients with much more insight into their credit portfolios than they have had historically.”

The credit-related data dates back to 2001 and thus spans different credit cycles including one extreme: the 2008 crisis.

An advantage of neural networks, said Huntsman, is that they don't assume a normal distribution of data. Instead, they can be programmed to update weekly or even daily, thus taking in new data points much more frequently.

Similar to how human brains function, neural networks process new data in layers, with each layer containing multiple nodes. The 55 loan variables pass through the nodes in the first layer, each filtering and transforming input for the next layer, which subsequently processes input from prior nodes until a final layer produces loan predictions.

The last layer decides on whether the loan will default or not. If it decides there's a high probability of default, but in fact that never happens, a loss function proceeds to determine how inaccurate the prediction was and adjusts parameters in each node accordingly. Then the data is fed back through the network of nodes, and the next predictions it generates should be much more accurate.

Getting to Why

In a random forest model, the algorithm knows whether a loan has defaulted or not – the training set – and seeks to determine why by analyzing the 55 loan variables to see which ones made a difference. To do this, the algorithm splits the data, looking at each variable until it comes up with the best mix. It may determine that loans under $100,000 are not likely to default, nor are those whose borrowers have credit scores higher than 700.

“It's machine learning because it has to learn what those splits are, and which splits are most important,” Huntsman explained. “A random forest is nothing more than a group of decision trees, where you take all the loan data, split it X number of ways and create X number of trees.”

The algorithm then searches the different trees to find the data in common, which provides a likely indication for why a loan defaulted or became delinquent.

The random forest model is applied to non-defaulted loans. The 55 attributes are fed into the algorithm, trained to predict defaults, and the decision points for each split applied to non-defaulted loans. The borrower payment history is also incorporated into the model and could provide an important input if, for example, a borrower has a history of making payments on time.

“That serves as an additional tool to try to determine which of those borrowers could potentially default,” Huntsman said.

Responsive to Changes

Those inputs change over time, creating new stresses on borrowers. The high accuracy rates of Synechron's models suggest that they are successfully incorporating those changes.

“A machine learning model can adapt to a changing environment, and it's a big advantage to have adaptive models,” Huntsman said, adding that prior to the financial crisis, such models likely would have seen upticks in key indicators such as delinquency rates.

The term “accelerator” is apt in this case, he said, because the firm has essentially developed all the code necessary to implement the model in clients' existing systems. That amounts to a “git,” or a repository of algorithms that clients can use as a foundation and later customize.

“A client may not want to use the neural network we built, or it may have its own customer data, or different attributes they want to feed into the model,” Huntsman said.

A Human Responsibility

He noted that machine learning is a step toward full-blown AI, in which the computer is capable of autonomous reasoning and decision-making. Machine learning still requires a programmer to write the code and set parameters for how the machine learns over time.

Huntsman said full-blown AI is not in the foreseeable future, because humans ultimately will remain responsible for credit-related decisions. Synechron's tools learn how to analyze huge volumes of data more effectively and dynamically, but their intent is to alert humans to the critical data.

“In banking, there's a strong need for humans, and accordingly there's a strong need to give humans more information,” Huntsman said.

The Securities Industry Essentials (SIE or Essentials) Exam is a new FINRA exam for prospective securities industry professionals. This introductory-level exam assesses a candidate’s knowledge of basic securities industry information including concepts fundamental to working in the industry, such as types of products and their risks; the structure of the securities industry markets, regulatory agencies and their functions; and prohibited practices.

Passing the Essentials exam alone does not qualify an individual for registration with a FINRA member firm or to engage in securities business. In order to become registered to engage in securities business, an individual must pass the Essentials exam and a qualification exam appropriate for the type of business the individual will engage in. The individual must be associated with a member firm to take a qualification exam.

Exposure Draft - Developing an Effective Managerial Costing System for Your Organization
Despite vast changes in the business environment during the past 50 years, the managerial costing practices used by many companies today are not much different than they were 10 or even 50 years ago. The cost information used to support critical management decisions continues to be based on financial accounting numbers that fail to consider the complexities of the business operations.

This Statement on Management Accounting (SMA) Exposure Draft by the IMA® (Institute of Management Accountants) Strategic Cost Management Task Force looks at managerial costing practices and answers the question, “How do managers decide which costing practices are best for their organization?” Applying IMA’s Conceptual Framework for Managerial Costing, it offers a six-step methodology organizations can use to develop a costing system appropriate for their management purposes.

The six-step process includes:
Doing a quick assessment of the current costing system’s effectiveness
Analyzing the organization’s strategy and business environment
Considering managerial cost modeling concepts
Evaluating the current managerial costing practices
Designing the appropriate level of costing system complexity for the organization
Implementing the new system across the organization
Management accountants can use this process as a guide for successful designing and implementing an effective managerial costing system for their organization.

FRM® certification sets you apart in the global marketplace and helps you move ahead. Certified FRMs have achieved positions such as Chief Risk Officer, Senior Risk Analyst, Head of Operational Risk and Director of Risk Management. In demonstrating your expertise and commitment to better risk practices, you also join a world-wide community dedicated to improved financial stability.
Ken School of Investment and Risk Studies provide professional tutors for FRM program. Comprehensive Preparation with conceptual training and Professional Guidance
Relax fee Structures for Students and Professionals

--------------------------------------------------------------------------------------------------------------------------------
The Chartered Financial Analyst (CFA) charter is an investment credential that, for more than 60 years, has been the global standard for embodying the integrity, dedication, and advanced skills needed to build a stronger, more accountable financial industry. No credential is as widely respected for its focus on current investment expertise and performing in the client’s best interest. None is harder to obtain.
Ken School of Investment and Risk Studies provide professional tutors for CFA program. Comprehensive Preparation with conceptual training and Professional Guidance
Relax fee Structures for Students and Professionals

The biggest U.S. banks may be on their way to a new capital standard for derivatives trading that addresses industry complaints that Wall Street’s risk-taking has been overestimated.

The Federal Reserve and two other agencies on Tuesday proposed a new approach meant to answer concerns that existing requirements ignore risk-reducing collateral and didn’t allow enough netting of derivatives contracts with similar risks. The change would free up some of the bank capital demanded after the 2008 financial crisis.

The new calculation, known as the “standardized approach for counterparty credit risk,” or SA-CCR, would be used in key capital measures, including how banks determine how much they need to offset risks and how close they’re getting to regulators’ leverage limits.
The Fed, Office of the Comptroller of the Currency and Federal Deposit Insurance Corp. say they’re trying to fix a system that doesn’t fit with today’s markets and regulatory demands -- and that hasn’t been adjusted since the crisis.
“This can result in a significant mismatch between the risk posed by these portfolios and the regulatory capital that the banking organization must hold against them,” the agencies said in their 248-page proposal.
Companies required to have the new method in place by July 1, 2020, are giant, global lenders identified as “advanced approaches” banks under capital rules -- including JPMorgan Chase & Co., Citigroup Inc. and Goldman Sachs Group Inc. That category is expected to be significantly narrowed in a separate regulatory plan set to be released this week, people familiar with that effort have said.
A Treasury Department report released last year encouraged regulators to adopt the SA-CCR, which could save the industry a tremendous amount of capital that the biggest banks now maintain against derivatives contracts.
The proposal released for a 60-day public comment period also represents the U.S. answer to a global agreement at the Basel Committee on Banking Supervision in 2014, where the approach was first established.

U.K. Targeting Lawyers, Accountants in Illicit Funds Crackdown

The British government says it is targeting accountants, lawyers and real estate agents who help hide dirty money as part of an increasingly aggressive effort to crack down on illicit fund flows from Russia, China and elsewhere.

Ken School of Risk & Investment Studies offers CFA, FRM, PRM courses. We are specialist for Risk and Investment studies.