{"id":{"repo_id":"soton","oai_identifier":"oai:eprints.soton.ac.uk:170515"},"canonical_url":"https://search.dev.ndltd.org/etd/soton/oai:eprints.soton.ac.uk:170515","repository":{"repo_id":"soton","name":"University of Southampton","base_url":"https://eprints.soton.ac.uk/cgi/oai2"},"display":{"title":"Credit risk models for mortgage loan loss given default","abstract":"Arguably, the credit risk models reported in the literature for the retail lending
sector have so far been less developed than those for the corporate sector,
mainly due to the lack of publicly available data. Having been given access to a
dataset on defaulted mortgages kindly provided by a major UK bank, this work
first investigates the Loss Given Default (LGD) of mortgage loans with the
development of two separate component models, the Probability of Repossession
(given default) Model and the Haircut (given repossession) Model. They are then
combined into an expected loss percentage. Performance-wise, this two-stage
LGD model is shown to do better than a single-stage LGD model (which directly
models LGD from loan and collateral characteristics), as it achieves a better Rsquare
value, and it more accurately matches the distribution of observed LGD.
We next investigate the possibility of including macroeconomic variables into
either or both component models to improve LGD prediction. Indicators relating
to net lending, gross domestic product, national default rates and interest rates
are considered and the interest rate is found to be most beneficial to both
component models. Finally, we develop a competing risk survival analysis model
to predict the time taken for a defaulted mortgage loan to reach some outcome
(i.e. repossession or non-repossession). This allows for a more accurate
prediction of (discounted) loss as these periods could vary from months to years
depending on the health of the economy. Besides loan- or collateral-related
characteristics, we incorporate a time-dependent macroeconomic variable based
on the house price index (HPI) to investigate its impact on repossession risk. We
find that observations of different loan-to-value ratios at default and different
security type are affected differently by the economy. This model is then used
for stress test purposes by applying a Monte Carlo simulation, and by varying the
HPI forecast, to get different loss distributions for different economic outlooks.","abstract_html":"Arguably, the credit risk models reported in the literature for the retail lending<br/>sector have so far been less developed than those for the corporate sector,<br/>mainly due to the lack of publicly available data. Having been given access to a<br/>dataset on defaulted mortgages kindly provided by a major UK bank, this work<br/>first investigates the Loss Given Default (LGD) of mortgage loans with the<br/>development of two separate component models, the Probability of Repossession<br/>(given default) Model and the Haircut (given repossession) Model. They are then<br/>combined into an expected loss percentage. Performance-wise, this two-stage<br/>LGD model is shown to do better than a single-stage LGD model (which directly<br/>models LGD from loan and collateral characteristics), as it achieves a better Rsquare<br/>value, and it more accurately matches the distribution of observed LGD.<br/>We next investigate the possibility of including macroeconomic variables into<br/>either or both component models to improve LGD prediction. Indicators relating<br/>to net lending, gross domestic product, national default rates and interest rates<br/>are considered and the interest rate is found to be most beneficial to both<br/>component models. Finally, we develop a competing risk survival analysis model<br/>to predict the time taken for a defaulted mortgage loan to reach some outcome<br/>(i.e. repossession or non-repossession). This allows for a more accurate<br/>prediction of (discounted) loss as these periods could vary from months to years<br/>depending on the health of the economy. Besides loan- or collateral-related<br/>characteristics, we incorporate a time-dependent macroeconomic variable based<br/>on the house price index (HPI) to investigate its impact on repossession risk. We<br/>find that observations of different loan-to-value ratios at default and different<br/>security type are affected differently by the economy. This model is then used<br/>for stress test purposes by applying a Monte Carlo simulation, and by varying the<br/>HPI forecast, to get different loss distributions for different economic outlooks.","abstract_has_math":false,"creators":["Leow, Mindy"],"institution":"University of Southampton","degree_name":"Ph.D.","degree_level":"doctoral","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Mues, Christophe","Thomas, Lyn"],"committee_chairs":[],"committee_members":[],"year":2010,"date_issued":"2010-08","date_published":"2010-08","updated_at":"2026-07-24T04:36:21Z","subjects":[],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Mues, Christophe","Thomas, Lyn"]},{"key":"dc:creator","label":"Author","values":["Leow, Mindy"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2010-08"]},{"key":"dc:date.issued","label":"Date","values":["2010-08"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["Management (pre 2011 reorg)","School of Management"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["University of Southampton"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["https://eprints.soton.ac.uk/170515/"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["doctoral"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["Ph.D."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://eprints.soton.ac.uk/170515/1/Final_PhD_Thesis_-_Mindy_Leow_October_2010.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Arguably, the credit risk models reported in the literature for the retail lending
sector have so far been less developed than those for the corporate sector,
mainly due to the lack of publicly available data. Having been given access to a
dataset on defaulted mortgages kindly provided by a major UK bank, this work
first investigates the Loss Given Default (LGD) of mortgage loans with the
development of two separate component models, the Probability of Repossession
(given default) Model and the Haircut (given repossession) Model. They are then
combined into an expected loss percentage. Performance-wise, this two-stage
LGD model is shown to do better than a single-stage LGD model (which directly
models LGD from loan and collateral characteristics), as it achieves a better Rsquare
value, and it more accurately matches the distribution of observed LGD.
We next investigate the possibility of including macroeconomic variables into
either or both component models to improve LGD prediction. Indicators relating
to net lending, gross domestic product, national default rates and interest rates
are considered and the interest rate is found to be most beneficial to both
component models. Finally, we develop a competing risk survival analysis model
to predict the time taken for a defaulted mortgage loan to reach some outcome
(i.e. repossession or non-repossession). This allows for a more accurate
prediction of (discounted) loss as these periods could vary from months to years
depending on the health of the economy. Besides loan- or collateral-related
characteristics, we incorporate a time-dependent macroeconomic variable based
on the house price index (HPI) to investigate its impact on repossession risk. We
find that observations of different loan-to-value ratios at default and different
security type are affected differently by the economy. This model is then used
for stress test purposes by applying a Monte Carlo simulation, and by varying the
HPI forecast, to get different loss distributions for different economic outlooks."]},{"key":"dc:format","label":"Dc Format","values":["text"]},{"key":"dc:title","label":"Title","values":["Credit risk models for mortgage loan loss given default"]}]}],"canonical_facts":{"dc:contributor.advisor":["Mues, Christophe","Thomas, Lyn"],"dc:creator":["Leow, Mindy"],"dc:date":["2010-08"],"dc:date.issued":["2010-08"],"dc:description.abstract":["Arguably, the credit risk models reported in the literature for the retail lending
sector have so far been less developed than those for the corporate sector,
mainly due to the lack of publicly available data. Having been given access to a
dataset on defaulted mortgages kindly provided by a major UK bank, this work
first investigates the Loss Given Default (LGD) of mortgage loans with the
development of two separate component models, the Probability of Repossession
(given default) Model and the Haircut (given repossession) Model. They are then
combined into an expected loss percentage. Performance-wise, this two-stage
LGD model is shown to do better than a single-stage LGD model (which directly
models LGD from loan and collateral characteristics), as it achieves a better Rsquare
value, and it more accurately matches the distribution of observed LGD.
We next investigate the possibility of including macroeconomic variables into
either or both component models to improve LGD prediction. Indicators relating
to net lending, gross domestic product, national default rates and interest rates
are considered and the interest rate is found to be most beneficial to both
component models. Finally, we develop a competing risk survival analysis model
to predict the time taken for a defaulted mortgage loan to reach some outcome
(i.e. repossession or non-repossession). This allows for a more accurate
prediction of (discounted) loss as these periods could vary from months to years
depending on the health of the economy. Besides loan- or collateral-related
characteristics, we incorporate a time-dependent macroeconomic variable based
on the house price index (HPI) to investigate its impact on repossession risk. We
find that observations of different loan-to-value ratios at default and different
security type are affected differently by the economy. This model is then used
for stress test purposes by applying a Monte Carlo simulation, and by varying the
HPI forecast, to get different loss distributions for different economic outlooks."],"dc:format":["text"],"dc:identifier.uri":["https://eprints.soton.ac.uk/170515/1/Final_PhD_Thesis_-_Mindy_Leow_October_2010.pdf"],"dc:publisher.department":["Management (pre 2011 reorg)","School of Management"],"dc:publisher.institution":["University of Southampton"],"dc:relation.isreferencedby":["https://eprints.soton.ac.uk/170515/"],"dc:title":["Credit risk models for mortgage loan loss given default"],"dc:type":["Thesis"],"dc:type.qualificationlevel":["doctoral"],"dc:type.qualificationname":["Ph.D."]},"updated_at":"2026-07-24T04:36:21Z"}