MReport May 2017

TheMReport — News and strategies for the evolving mortgage marketplace.

Issue link:

Contents of this Issue


Page 27 of 67

26 | TH E M R EP O RT FEATURE BEST IN ORIGINATION Waterstone Mortgage Corporation borrowers and unpaid balance of the loan weren't as powerful for forecasting future defaults among these loans. In other words, by analyzing the data, we are able to deduce that economic variables are far more important than bor - rower characteristics in evaluating the performance of mortgages after modification. It is possible to benchmark these results against performance on holdout test data. After splitting the data 80-20, an analyst can train an XGBoost model on 80 percent of the data. The analyst can then compare the actual default rates against the XGBoost predictions for the remaining "unseen" portion of the data. Using a standard receiver operating characteristic (ROC) curve, it is possible to evaluate and compare model performance. An ROC curve works by plot - ting the true positive rate (how many predictions the model got correct) against the true negative rate (how many predictions the model estimated to occur that did not). The technique is often used for optimal model selection. The closer the curve is to a 45-degree line, the worse it performs. Here we see, in Figure 2, that the speci - ficity (or the true positive rate), as well as the sensitivity (the true negative rate), are nearly ideal. The XGBoost model is nearly optimal. Compare these results with the ROC curve of a traditional scoring algorithm such as logistic regres - sion, shown in Figure 3. The predictions from the tradi- tional algorithm aren't as accurate as those of the XGBoost model. The ROC curve from the traditional algorithm is much closer to the di- agonal, meaning that the true posi- tive and true negative rates aren't performing as well. XGBoost has an advantage over the traditional algorithm in this holdout data set. The Future Depends on Predictive Analytics T he XGBoost model, like similar algorithms, is easy to implement. Once the mechanics of the technique are understood, and the parameters are tuned cor - rectly, the model can be turned on a data set to produce accom- panying predictions. The model can be updated continuously each month based on new data feeds. Pointing an XGBoost program toward a new data set and run - ning it again is virtually all that is needed to refresh the results. It is also possible to retune the pa- rameters for the update to further enhance the effects. Figure 1: XGBoost ROC Curve Figure 2: Logistic ROC Curve "Considering the growing amounts of data available, the mortgage industry should pay attention to predictive analytics tools." A use case of this type of model would be to pursue early buyouts for mortgages that have a high probability of re-performing and potentially not pursue early buyouts for mortgages that have a low probability of re-performing, as long as this policy is consistent with GNMA servicing guidelines. This same technique can be used on a variety of data for alter - native purposes. Predictive analyt- ics can capture predictive power from internal data, whether that involves established and go-to data sets or whether that involves bringing together data from across an organization to make predic - tions. Predictive analytics can also help a firm leverage industry data and other outside sources to fore- cast trends or improve decisions. This case is a concrete example of how using the tool should result in higher return on investment on GNMA early buyouts. Considering the growing amounts of data available, the mortgage industry should pay attention to predictive analytics tools. Investing in the technology has proven to generate significant returns. GNMA issuers is just one group to which predictive analyt - ics can be applied. Predictive analytics can be applied to many other techniques and tools to increase efficiencies within the mortgage industry. The future depends on it. JONATHAN B. GLOWACKI, FSA , CERA , MAAA is a principal and consulting actuary with Milliman, and a fellow and chartered enterprise risk analyst through the Society of Actuaries. Glowacki's areas of expertise include mortgage scoring, structured finance, model validation, and loan-loss reserving. He has provided quantitative and strategic consulting services on topics including residential mortgage collateral, credit insurance, debt protection products, reverse mortgages, mortgage insurance, financial guaranty insurance, deposit insurance, commercial mortgage-backed securities, and financial institution credit risk. MAKHO MASHOBA is a financial analyst with Milliman. He joined the firm in 2016, special - izing in econometrics and the statistical analysis of consumer behavior. Mashoba has worked on projects involving model validation as well as borrower risk evaluation and mortgage industry trend analysis.

Articles in this issue

Archives of this issue

view archives of TheMReport - MReport May 2017