Matches in SemOpenAlex for { <https://semopenalex.org/work/W3159804568> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W3159804568 abstract "Machine learning methods are explored in an attempt to achieve better predictive performance than the legacy rule-based fraud detection systems that are currently used to detect fraudulent car insurance claims. There are two key principles that lead the exploration of machine learning techniques and algorithms in this thesis, namely, the applicability to imbalanced data, and the interpretability of predictions. The dataset used for model training and evaluation contains only 0.3% fraudulent claims compared to 99.7% non-fraudulent claims, which can therefore be considered highly imbalanced. Furthermore, prediction interpretability is of great importance, since fraud experts are directly interfacing with the output of the machine learning models. With the key principles in mind, this thesis considers four algorithms, Logistic Regression, Random Forest, LightGBM and a Stacking classifier. The algorithms are trained on the imbalanced learning problem by using a combination of undersampling (random and Edited Nearest Neighbors), oversampling (SMOTE) and class weighting. Conclusively, each trained model meets the objective, with the Stacking classifier combining the best performance with the lowest variance. By benchmarking the baseline for two different parameters, the models can be evaluated for two boundary conditions, which leads to tunable performance between the two conditions. Ultimately, the performance of the Stacking classifier is tunable (by moving its classification threshold) to roughly a 70-80% increase in extra fraud caught or a 75% reduction in effort. Extra fraud will increase the amount of real fraudulent claims that fraud experts get to see, and effort reduction leads to an increase in capacity, which enables fraud experts to spend more time on other more relevant tasks." @default.
- W3159804568 created "2021-05-10" @default.
- W3159804568 creator A5065900619 @default.
- W3159804568 date "2018-01-01" @default.
- W3159804568 modified "2023-09-27" @default.
- W3159804568 title "The Future of Fraud Detection: Detecting Fraudulent Insurance Claims Using Machine Learning Methods" @default.
- W3159804568 hasPublicationYear "2018" @default.
- W3159804568 type Work @default.
- W3159804568 sameAs 3159804568 @default.
- W3159804568 citedByCount "0" @default.
- W3159804568 crossrefType "journal-article" @default.
- W3159804568 hasAuthorship W3159804568A5065900619 @default.
- W3159804568 hasConcept C119857082 @default.
- W3159804568 hasConcept C124101348 @default.
- W3159804568 hasConcept C136536468 @default.
- W3159804568 hasConcept C154945302 @default.
- W3159804568 hasConcept C169258074 @default.
- W3159804568 hasConcept C197323446 @default.
- W3159804568 hasConcept C2776257435 @default.
- W3159804568 hasConcept C2781067378 @default.
- W3159804568 hasConcept C31258907 @default.
- W3159804568 hasConcept C41008148 @default.
- W3159804568 hasConcept C95623464 @default.
- W3159804568 hasConceptScore W3159804568C119857082 @default.
- W3159804568 hasConceptScore W3159804568C124101348 @default.
- W3159804568 hasConceptScore W3159804568C136536468 @default.
- W3159804568 hasConceptScore W3159804568C154945302 @default.
- W3159804568 hasConceptScore W3159804568C169258074 @default.
- W3159804568 hasConceptScore W3159804568C197323446 @default.
- W3159804568 hasConceptScore W3159804568C2776257435 @default.
- W3159804568 hasConceptScore W3159804568C2781067378 @default.
- W3159804568 hasConceptScore W3159804568C31258907 @default.
- W3159804568 hasConceptScore W3159804568C41008148 @default.
- W3159804568 hasConceptScore W3159804568C95623464 @default.
- W3159804568 hasLocation W31598045681 @default.
- W3159804568 hasOpenAccess W3159804568 @default.
- W3159804568 hasPrimaryLocation W31598045681 @default.
- W3159804568 hasRelatedWork W2176987356 @default.
- W3159804568 hasRelatedWork W2209122160 @default.
- W3159804568 hasRelatedWork W2405680064 @default.
- W3159804568 hasRelatedWork W2956736547 @default.
- W3159804568 hasRelatedWork W2966244084 @default.
- W3159804568 hasRelatedWork W2969256340 @default.
- W3159804568 hasRelatedWork W2972164914 @default.
- W3159804568 hasRelatedWork W3040530723 @default.
- W3159804568 hasRelatedWork W3050989012 @default.
- W3159804568 hasRelatedWork W3082648102 @default.
- W3159804568 hasRelatedWork W3090638973 @default.
- W3159804568 hasRelatedWork W3097282267 @default.
- W3159804568 hasRelatedWork W3109744303 @default.
- W3159804568 hasRelatedWork W3110463245 @default.
- W3159804568 hasRelatedWork W3117060406 @default.
- W3159804568 hasRelatedWork W3128454533 @default.
- W3159804568 hasRelatedWork W3136239615 @default.
- W3159804568 hasRelatedWork W3136437899 @default.
- W3159804568 hasRelatedWork W3157195272 @default.
- W3159804568 hasRelatedWork W3178483058 @default.
- W3159804568 isParatext "false" @default.
- W3159804568 isRetracted "false" @default.
- W3159804568 magId "3159804568" @default.
- W3159804568 workType "article" @default.