{"id":{"repo_id":"toronto-retro","oai_identifier":"oai:utoronto.scholaris.ca:1807/103451"},"canonical_url":"https://search.dev.ndltd.org/etd/toronto-retro/oai:utoronto.scholaris.ca:1807/103451","repository":{"repo_id":"toronto-retro","name":"University of Toronto","base_url":"https://utoronto.scholaris.ca/server/oai/request"},"display":{"title":"A Class of Mixture of Experts Models for General Insurance Ratemaking and Reserving","abstract":"Understanding the effect of policyholders' risk profile on the number and the amount of claims, as well as the dependence among different types of claims, are critical to insurance ratemaking and IBNR-type reserving. To accurately quantify such features, it is essential to develop a regression model which is flexible, interpretable and statistically tractable. In this thesis, we first propose a highly flexible nonlinear regression model, namely the logit-weighted reduced mixture of experts (LRMoE) models, for multivariate claim frequencies or severities distributions. The LRMoE model is interpretable as it has two components: Gating functions to classify policyholders into various latent sub-classes and Expert functions to govern the distributional properties of the claims. The model is also flexible to fit any types of claim data accurately and hence minimize the issue of model selection. Model implementation is then illustrated in two ways using a real automobile insurance dataset from a major European insurance company. We first fit the multivariate claim frequencies using an Erlang count expert function. Apart from showing excellent fitting results, we can interpret the fitted model in an insurance perspective and visualize the relationship between policyholders' information and their risk level. We further demonstrate how the fitted model may be useful for insurance ratemaking. The second illustration deals with insurance loss severity data that often exhibits heavy-tail behavior. Using a Transformed Gamma expert function, our model is applicable to fit the severity and reporting delay components of the dataset, which is ultimately shown to be useful and crucial for an adequate prediction of IBNR reserve. After that, we further extend the fitting algorithm to efficiently fit the LRMoE to random censored and truncated regression data. Such an extended algorithm is then found useful and important for broader actuarial applications such as unbiased claim reporting delay modeling and deductible ratemaking.","abstract_html":"Understanding the effect of policyholders' risk profile on the number and the amount of claims, as well as the dependence among different types of claims, are critical to insurance ratemaking and IBNR-type reserving. To accurately quantify such features, it is essential to develop a regression model which is flexible, interpretable and statistically tractable. In this thesis, we first propose a highly flexible nonlinear regression model, namely the logit-weighted reduced mixture of experts (LRMoE) models, for multivariate claim frequencies or severities distributions. The LRMoE model is interpretable as it has two components: Gating functions to classify policyholders into various latent sub-classes and Expert functions to govern the distributional properties of the claims. The model is also flexible to fit any types of claim data accurately and hence minimize the issue of model selection. Model implementation is then illustrated in two ways using a real automobile insurance dataset from a major European insurance company. We first fit the multivariate claim frequencies using an Erlang count expert function. Apart from showing excellent fitting results, we can interpret the fitted model in an insurance perspective and visualize the relationship between policyholders' information and their risk level. We further demonstrate how the fitted model may be useful for insurance ratemaking. The second illustration deals with insurance loss severity data that often exhibits heavy-tail behavior. Using a Transformed Gamma expert function, our model is applicable to fit the severity and reporting delay components of the dataset, which is ultimately shown to be useful and crucial for an adequate prediction of IBNR reserve. After that, we further extend the fitting algorithm to efficiently fit the LRMoE to random censored and truncated regression data. Such an extended algorithm is then found useful and important for broader actuarial applications such as unbiased claim reporting delay modeling and deductible ratemaking.","abstract_has_math":false,"creators":["Fung, Tsz Chai"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Statistics","school":null,"contributors":[],"advisors":["Lin, X. Sheldon","Badescu, Andrei L."],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-11","date_published":"2020-11","updated_at":"2026-07-27T21:27:54Z","subjects":["Claim frequency and severity modeling","Denseness theory","Mixture of Experts Models","Multivariate regression analysis","Property and Casualty Insurance"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1807/103451","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Lin, X. Sheldon","Badescu, Andrei L."]},{"key":"dc:contributor.department","label":"Department","values":["Statistics"]},{"key":"dc:creator","label":"Author","values":["Fung, Tsz Chai"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-11"]},{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2020-11-30T19:50:46Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2020-11-30T19:50:46Z"]},{"key":"dc:date.issued","label":"Date","values":["2020-11"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Claim frequency and severity modeling","Denseness theory","Mixture of Experts Models","Multivariate regression analysis","Property and Casualty Insurance"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1807/103451"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Understanding the effect of policyholders' risk profile on the number and the amount of claims, as well as the dependence among different types of claims, are critical to insurance ratemaking and IBNR-type reserving. To accurately quantify such features, it is essential to develop a regression model which is flexible, interpretable and statistically tractable. In this thesis, we first propose a highly flexible nonlinear regression model, namely the logit-weighted reduced mixture of experts (LRMoE) models, for multivariate claim frequencies or severities distributions. The LRMoE model is interpretable as it has two components: Gating functions to classify policyholders into various latent sub-classes and Expert functions to govern the distributional properties of the claims. The model is also flexible to fit any types of claim data accurately and hence minimize the issue of model selection. Model implementation is then illustrated in two ways using a real automobile insurance dataset from a major European insurance company. We first fit the multivariate claim frequencies using an Erlang count expert function. Apart from showing excellent fitting results, we can interpret the fitted model in an insurance perspective and visualize the relationship between policyholders' information and their risk level. We further demonstrate how the fitted model may be useful for insurance ratemaking. The second illustration deals with insurance loss severity data that often exhibits heavy-tail behavior. Using a Transformed Gamma expert function, our model is applicable to fit the severity and reporting delay components of the dataset, which is ultimately shown to be useful and crucial for an adequate prediction of IBNR reserve. After that, we further extend the fitting algorithm to efficiently fit the LRMoE to random censored and truncated regression data. Such an extended algorithm is then found useful and important for broader actuarial applications such as unbiased claim reporting delay modeling and deductible ratemaking."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ph.D."]},{"key":"dc:title","label":"Title","values":["A Class of Mixture of Experts Models for General Insurance Ratemaking and Reserving"]}]}],"canonical_facts":{"dc:contributor.advisor":["Lin, X. Sheldon","Badescu, Andrei L."],"dc:contributor.department":["Statistics"],"dc:creator":["Fung, Tsz Chai"],"dc:date":["2020-11"],"dc:date.accessioned":["2020-11-30T19:50:46Z"],"dc:date.available":["2020-11-30T19:50:46Z"],"dc:date.issued":["2020-11"],"dc:description.abstract":["Understanding the effect of policyholders' risk profile on the number and the amount of claims, as well as the dependence among different types of claims, are critical to insurance ratemaking and IBNR-type reserving. To accurately quantify such features, it is essential to develop a regression model which is flexible, interpretable and statistically tractable. In this thesis, we first propose a highly flexible nonlinear regression model, namely the logit-weighted reduced mixture of experts (LRMoE) models, for multivariate claim frequencies or severities distributions. The LRMoE model is interpretable as it has two components: Gating functions to classify policyholders into various latent sub-classes and Expert functions to govern the distributional properties of the claims. The model is also flexible to fit any types of claim data accurately and hence minimize the issue of model selection. Model implementation is then illustrated in two ways using a real automobile insurance dataset from a major European insurance company. We first fit the multivariate claim frequencies using an Erlang count expert function. Apart from showing excellent fitting results, we can interpret the fitted model in an insurance perspective and visualize the relationship between policyholders' information and their risk level. We further demonstrate how the fitted model may be useful for insurance ratemaking. The second illustration deals with insurance loss severity data that often exhibits heavy-tail behavior. Using a Transformed Gamma expert function, our model is applicable to fit the severity and reporting delay components of the dataset, which is ultimately shown to be useful and crucial for an adequate prediction of IBNR reserve. After that, we further extend the fitting algorithm to efficiently fit the LRMoE to random censored and truncated regression data. Such an extended algorithm is then found useful and important for broader actuarial applications such as unbiased claim reporting delay modeling and deductible ratemaking."],"dc:description.degree":["Ph.D."],"dc:identifier.uri":["http://hdl.handle.net/1807/103451"],"dc:subject":["Claim frequency and severity modeling","Denseness theory","Mixture of Experts Models","Multivariate regression analysis","Property and Casualty Insurance"],"dc:title":["A Class of Mixture of Experts Models for General Insurance Ratemaking and Reserving"],"dc:type":["Thesis"]},"updated_at":"2026-07-27T21:27:54Z"}