Repository navigation
Conversation
Work in progress: a CECL allowance model for a synthetic residential mortgage portfolio, driven by FRED macro history and the Fed 2025 supervisory scenarios, with ten custom validation tests. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Split pre-2020 performance into train and test samples by loan, keeping 2020 onwards out of time. Add a logistic challenger for the default, prepayment and LGD models, compared with the champion on AUC, the allowance and the CECL tests. Models are fitted in cecl_train.py and saved with joblib, so other notebooks can load the same models; the saved file is refitted when missing, stale or from another scikit-learn version. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- WOEInformationValue: Weight of Evidence by bin and Information Value per driver, implemented directly with no binning library - MacroShockSensitivity: allowance under single-driver unemployment, house price and mortgage rate shocks, plus a combined shock, with direction checks - HistoricalReplay: replays the early-1990s recession, 2008 crisis and pandemic on today's portfolio and checks severely adverse is at least as severe - ReverseStress: finds the combined shock severity that multiplies the baseline allowance by a given factor - cecl_model: split scenario path building into reusable helpers (scenario, historical and shocked changes) so the stress tests share the same engine; scenario paths are unchanged Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Pull Request Description
What and why?
Work in progress. Adds a notebook that documents a CECL lifetime loss model for a synthetic residential mortgage portfolio, using FRED macro history and the Fed 2025 supervisory scenarios, plus ten custom validation tests for it.
How to test
What needs special review?
Dependencies, breaking changes, and deployment notes
Release notes
Checklist
🤖 Generated with Claude Code