Publication

Risk Integrated Applies Artificial Intelligence to CRE Risk

Risk Integrated has exploited the advances in machine learning (ML) to characterize the credit risk of commercial real estate lending. This has been achieved by using Risk Integrated’s comprehensive cashflow and risk simulation models in the Specialized Finance System (SFS). With the SFS we generate a massive dataset for pre-training the machine learning models and predict default events based on the characteristics of the underlying properties, leases and loans. A combination of Neural Networks and Fine Decision Trees were found to give the best characterization of the complex nonlinear, discontinuous risk profiles of commercial real estate transactions. This pre-training of the ML models has the advantage of improving the results with the finite real-world data.

In addition to pre-training ML models for credit risk data, Risk Integrated has adopted the machine learning approach to enhance the SFS by greatly reducing the time to get the results of the complex simulation models. Full simulation models have the great advantages of capturing all the details of complex commercial real estate structures, but on-the fly simulation of thousands of detailed scenarios can take several minutes. To speed the computation time, we have trained an ML network on the SFS to emulate the results. Emulation with machine learning has the great advantage that after training, evaluation of the risk requires a single pass through the neural net rather than running thousands of complex scenarios. This computation requires only milliseconds and greatly enhances the ability to run optimization analyses on large portfolios using the full sophistication of the underlying SFS analytics.

Based on these successes, Risk Integrated is now applying its AI tools to other aspects of transforming the commercial real estate market.

Dr. [...]

May 21st, 2018|

Risk Reporting for Equity Investors in Commercial Real Estate

Introduction
Risk Integrated has extended its well proven Specialized Finance System (SFS) to include equity risk metrics for commercial real estate. Over the last 16 years the SFS has been developed primarily to provide credit risk metrics such as probability of default and stress-loss for commercial mortgages using cashflow simulation. The credit metrics are based on the cashflows to the loans whereas the equity metrics are the “residual” cashflows to the property owners and include the effects of leveraging, interest rate swaps and currency effects for multi-currency portfolios.

For equity investors the SFS produces familiar metrics such as the internal rate of return and cash on cash return, in both the base-case and across thousands of possible market and tenant scenarios. The figures below illustrate the IRR for a deal without and with leverage.

Returns without Leverage

Returns with Leverage

The links below give the complete reports for the deals without and with leverage, and include the credit report on the debt for the leveraging loan.

Equity Report for Unleveraged Property Investment

Equity Report for Leveraged Property Investment

Credit Report for the Leveraging Loan

Dr. Chris Marrison
CEO, Risk Integrated
Chris.Marrison@RiskIntegrated.com

March 6th, 2018|

The Effect of Deal Structures on Current Expected Credit Loss

Introduction
In a recent paper, we looked at the effect of forecasts on IFRS-9 and Current Expected Credit Loss (CECL) deductions. This paper goes a step further to explore what lenders can do with deal structures to limit the expected losses. This can be viewed in three ways:

Approaches to reduce the CECL deductions
Approaches to reduce the actual risk
Approaches to arbitrage anyone who does not take these features into account

In the previous paper, we looked at several variations on a commercial real estate deal under three forecasts. In this paper, we take the most-risky combination and show the effect of changing the loan structure. The stylized "moderately negative" central forecast used was as follows:

Interest rates, inflation and vacancy rates increase 0.5% per year for three years and then flatten
Capital values and rental rates fall 5% per year for three years and then flatten

The loan is towards the risky end of the spectrum. It is for a Boston office with an LTV of 75%, initial DSCR of 1.35, floating-rate interest, 20-year amortization and a maturity of 5 years. There are four equal leases with a 1% probability of tenant default, one lease expiring in year three, the others expiring after year eight, and all leases repricing to the market annually.

Analysis
Using the Specialized Finance System's cashflow simulation, we quantified the effect of six variations in the financing structure:

Reduced loan amounts
Alternative amortization profiles
Interest rate caps
Sweep amortization (i.e., also taking all excess income to pay-down the loan)
Sweep triggered by covenants on Loan to Value (LTV)
Sweep triggered by covenants on Debt Service Coverage Ratio (DSCR)

The details of each variation are described later. Let us first look at the overall results. The table shows [...]

May 8th, 2017|

The Effect of Forecasts on IFRS-9 and Current Expected Credit Loss

Introduction
The Financial Accounting Standard Board's (FASB's) new IFRS-9 and the Current Expected Credit Loss (CECL) approach requires banks to deduct the Expected Loss from the balance-sheet value of a loan. Furthermore, it requires the Expected Loss to be estimated using a reasonable forecast of the future market. Now consider this recent quote on Bloomberg:

"Apartment rents in cities such as New York and San Francisco will need to fall as much as 15 percent for a glut of high-end developments to be absorbed, according to billionaire real estate investor Richard LeFrak"

This leads to questions as to how much difference do the forecasts make to the CECL and what kind of deals are most affected?

This short paper outlines the answers to those questions for commercial real estate by testing a range of mean-reverting forecasts against typical example deals. The approach used to assess the risk is the comprehensive cashflow simulation embedded in the Specialized Finance System (SFS). The simulation tests the deals under thousands of dispersed random scenarios, centered around forecasts for inflation, interest rates, capital values, rental rates and vacancy rates.

Analysis
Three simplified forecasts are used for illustration here:

Basecase:
Simulation is around a flat forecast relative to today

Mildly negative central forecast:
Interest rates, inflation and vacancy rates increase 0.25% per year for three years and then flatten
Capital values and rental rates fall 2.5% per year for three years and then flatten.

Moderately negative central forecast:

Interest rates, inflation and vacancy rates increase 0.5% per year for three years and then flatten
Capital values and rental rates fall 5% per year for three years and then flatten.

The loans are all for a Boston office with an LTV of 75%, initial DSCR of 1.35, 20-year amortization, [...]

April 5th, 2017|

How to Arbitrage Slotting Capital

Introduction
One of the options for allocating regulatory capital under Basel III and Solvency II is to use the "slotting" approach, whereby the capital for each asset is assigned according to a small number of slots, e.g., low, medium, and high risk. This creates specific behavior-incentives for the institutions under slotting and specific arbitrage opportunities for those institutions with more advanced approaches. This paper looks at the "game" set up by this set of incentives. The paper first summarizes the arbitrage opportunities and then explains the underlying rational. The opportunities are best explained on a graph.

Graph 1. Cost of Funds for Each Level of Measured Risk

In Graph 1 the x-axis is the riskiness as judged by the slotting criteria. The y-axis is the cost-of-funds. In Graph 1 the slotting cost-of-funds depends simply on the assigned capital per slot, multiplied by the required return on equity. For later discussion, the points on the steps are labeled as leading-edge and trailing-edge.

Graph 2. Range of Cost of Funds for Actual Risk

Graph 2 adds a range for the cost-of-funds. This range shows what the cost-of-funds (COF) would be if the risk was perfectly known. The true COF is different to the slotting COF for two reasons. Obviously the first reason is that the slots produce steps. The second reason is that the simplified risk assessments such as the typical slotting criteria do not capture all the possible risk variations within a deal: in a previous paper we demonstrated how the tenant, property and financial structures can produce great differences in risk for commercial property deals that seem to have identical risk according to conventional measures such as Loan [...]

June 22nd, 2016|

Risk Integrated Releases Quarterly CCAR Model for Commercial Real Estate

FOR IMMEDIATE RELEASE:

Risk Integrated Releases Quarterly CCAR Model for Commercial Real Estate

New York / London – May 19, 2016 – Risk Integrated, the leading international risk solution provider for commercial real estate, today announced the release of a quarterly cashflow simulation model (CFM) specifically tailored to the requirements of the US regulatory Comprehensive Capital Analysis and Review (CCAR) stress tests. In addition to breaking the risk into granular, quarterly time steps, this new model requires less input data and is easier to use and maintain.

The CCAR CFM is built on the same foundation as the comprehensive fully detailed CFM that clients are currently using in the Specialized Finance System (SFS) for grading and deal structuring as well as Basel III and Solvency II regulatory compliance. The full model takes into account the many features, such as covenants, lease terms, etc., which can change the risk of a commercial real estate financing, and are especially useful when structuring new credits. By building on the same foundation, the new CCAR CFM model leverages the proven track record of the full model (see Validation of the Specialized Finance System). However, the CCAR CFM has been optimized and greatly simplified such that it only requires data which is available from the CCAR dataset (the FR Y-14Q data).

At a portfolio level, the new model gives very similar results to the full model. The graph below illustrates a portfolio's cumulative loss, quarter by quarter, for the CCAR stress, comparing the quarterly losses with the average losses from annual time steps.

At this time there is increased regulatory pressure for institutions to only use capital models that they control and understand in full detail - i.e., not to [...]

May 19th, 2016|

Solvency II Compliance achieved with Risk Integrated’s Specialized Finance System

FOR IMMEDIATE RELEASE:

Solvency II Compliance achieved with Risk Integrated’s Specialized Finance System

New York / London – April 12, 2016 – Risk Integrated, the leading technology firm focused on risk measurement for commercial real estate, today announced that a leading global insurer has gained regulatory approval to use the Specialized Finance System as their internal model to calculate regulatory capital requirements under Solvency II. Risk Integrated’s Specialized Finance System (SFS) is also being used for gathering detailed data on its commercial real estate loans, reporting on the assets’ risk profile and structuring new loans.

At a time of increasing regulatory and risk management pressures, the client is using the SFS to strengthen the reporting of its commercial real estate (CRE) assets to give management, the board and regulators an increased understanding of the portfolio. They are also using the SFS to provide a competitive advantage when originating new transactions by gaining deeper insights into the sources of risk. A senior executive risk manager in the organisation commented that "We see the SFS as providing both regulatory compliance and a competitive advantage. This tool is a key factor for integrating all the aspects of risk management across the business".

At the core of the SFS there is a set of highly detailed cashflow simulation models. The models are transparent and under the control of the client's analysts to incorporate its business expertise. The resulting reports allow users to see the interaction of the risk factors within each deal's structure. Examples of detailed cashflow risk reports are shown at this link: Dissecting CRE Loan Risks

Dr. Yusuf Jafry, Risk Integrated's CTO, commented that "I am delighted that they have selected the SFS. [...]

April 12th, 2016|

The Effect of Tenant Defaults on CRE Loans

Introduction
In lending to commercial real estate (CRE), it is clear that the credit-worthiness of the building's tenants influences the overall risk of the deal. But then the question arises, "To what extent is a tenant's credit-worthiness important?" This paper answers the question by taking a series of deals and assessing their risk for different levels of tenant credit-worthiness. We also look at examples of how the impact the tenant quality is different for different levels of loan-to-value, number of tenants, and rental rates.

Base Deal
The first step is to define a standard deal and then assess the risk of the deal given different probabilities of the tenant defaulting (PTD). The standard deal is chosen as follows:

Property: Office in NY valued at $10,000,000 with prevailing market rent of $700,000/year
Lease: One tenant, paying $700,000/year (i.e., currently at market rent), expiring in 8 years
Loan: Balance of $7,000,000, paying 5% fixed, maturing in 10 years with 25 year amortization

The lowest PTD is set to be 0.1% and is then repeatedly doubled to create a range up to 51.2%. The risk is then assessed using Risk Integrated's Specialized Finance System (SFS), which runs a Monte Carlo simulation of a detailed CRE cashflow model to capture all property and loan details. Chart 1 shows the profile of the annual probability of default (PD) of the loan until the loan's maturity. For this graph, the PTD is set to be 1.6% in the first year.
Chart 1: Probability of Default Profile for the Base-deal with PTD=1.60%

In Chart 1 we see the following:

In year 1 the PD of the deal is 0.44%, i.e., much lower than the tenant's PD of 1.6%. This is because it is [...]

February 8th, 2016|

IFRS-9, CECL and Pro-cyclicality

Introduction
The International Accounting Standards Board (IASB) and the US Financial Accounting Standard Board (FASB) are updating the approach for setting Allowances for Loan and Lease Losses (ALLL). In International Financial Reporting Standard 9 (IFRS-9) the IASB require allowances to be set according to the lifetime credit losses weighted by the estimated probability of default 12-months from the reporting date. A modified version of this is FASB’s Current Expected Credit Loss Model (CECL). With CECL, FASB requires financial institutions to set their ALLL according to each transaction’s Expected Loss (EL). One of the effects of IASB-9 and CECL is that ALLL for unimpaired loans will increase during an economic recession. Depending on how the financial institution implements the PD or EL grading, from top to bottom of an economic cycle the ALLL may increase significantly, e.g., by a factor of 10. However, with more careful choices in the ratings framework, the increase in ALLL may be much smaller, e.g., less than a factor of 2. This has a very significant effect on the reported solvency of the bank. Critically, the degree of this pro-cyclical swing depends on the choices made when the rating framework is first implemented by the institution. This paper outlines why the swing occurs and recommends how rating frameworks should be designed to minimize pro-cyclicality.

The Inherent Pro-cyclical Nature of IFRS-9 and CECL
Currently banks assess their Allowance for Loan and Lease losses (ALLL) only for loans classified as impaired. With IFRS-9 and CECL, ALLL will be based on the Expected Loss (EL) for all loans, including those which are not currently impaired. One of the concerns of the American Bankers Association is that [...]

October 28th, 2015|

Cost-of-Funds for Commercial Real Estate

Introduction
This paper gives a brief introduction to cost-of-funds, (also known as transfer pricing) and the difficulties of setting the cost of funds for commercial real estate (CRE) lending operations. It then suggests a relatively straightforward approach which avoids these difficulties.
The Importance and Difficulty of Setting the Cost-of-Funds
The Cost-of-Funds (CoF) is the rate charged by the institution’s central treasury on money they give to individual lending units when those units request funds to lend on to customers. The CoF is the primary cost used in measuring a business unit’s profitability and typically it directly impacts the compensation of the lending teams. It therefore acts as a strong incentive in defining the nature of the assets being originated. Very simply:

The CoF has four potential components:

The risk-free rate for the term and rate profile of the loan to the customer
An operating cost
A subsidy from senior management to guide the relative growth of businesses
The cost of risk

This paper is focused on the cost of risk. A common practice is to link the cost of risk to the capital to be held for the asset. Pricing according to capital has several problems and is particularly difficult for CRE as CRE loans have long-terms and are highly-structured with time-varying risk profiles. Pricing according to the regulatory capital is especially problematic because regulatory capital typically only reflects the average risk of similar assets. The objective of regulatory capital is to ensure that the portfolio as a whole is backed by sufficient capital so regulatory capital does not necessarily reflect the risk of individual assets, and typically does not capture the changing risk profile of CRE assets over time. Regulatory decisions to require [...]

August 3rd, 2015|