Are securitization contracts boilerplate? Machine learning on CMBS pooling and servicing agreements (JFQA, 2024)

Every commercial mortgage-backed securities (CMBS) deal is governed by a pooling and servicing agreement (PSA): a long contract that defines how the pooled loans are held and serviced, how cash is allocated among bond classes, and what the servicer may do when a loan goes bad. The received view among many market participants is that the PSA is boilerplate, copied deal to deal with only the names changed, and therefore not worth reading closely. This paper, with Brent Ambrose, Yiqiang Han, and Sanket Korgaonkar, published in the Journal of Financial and Quantitative Analysis in 2024, tests that view by reading the contracts with machines.

What we did

We introduce a machine-learning comparison of PSAs. Instead of selecting a few clauses by hand, the method compares entire documents to one another and measures how far each agreement departs from the others. This produces a measure of contract variation that can be related to deal characteristics and to outcomes.

What we found

The PSA is not boilerplate. We document substantial variation across agreements, both within and across underwriters and over time. A part of the variation is explained by differences in loan collateral across deals, which is what one would expect if contracts are tailored to the risks in the pool. The rest is not mechanical.

Most importantly, differences in PSAs are correlated with ex-post loan and bond performance. The contracts carry information about how the deal will fare that is not captured by the standard summary variables investors use.

Why it matters

The practical lesson is that the whole governing document matters. Analysis that focuses on specific components, or that assumes the agreement is standardized, misses information that is priced in outcomes. For investors, the paper argues for reading the contract; for regulators and rating agencies, it argues for treating contract text as data. Methodologically, it is an early example of the approach I later applied to listing remarks: use machine learning to measure a document at scale, and then ask an economic question about what the measure predicts. The two-step method I now use with large language models grew out of this work.