FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3158002759> ?p ?o ?g. }

• W3158002759 endingPage "81" @default.
• W3158002759 startingPage "60" @default.
• W3158002759 abstract "Although researchers increasingly use deep neural networks (DNN) to analyze individual choices, overfitting and interpretability issues remain obstacles in theory and practice. This study presents a statistical learning theoretical framework to examine the tradeoff between estimation and approximation errors, and between the quality of prediction and of interpretation. It provides an upper bound on the estimation error of the prediction quality in DNN, measured by zero-one and log losses, shedding light on why DNN models do not overfit. It proposes a metric for interpretation quality by formulating a function approximation loss that measures the difference between true and estimated choice probability functions. It argues that the binary logit (BNL) and multinomial logit (MNL) models are the specific cases of DNNs, since the latter always has smaller approximation errors. We explore the relative performance of DNN and classical choice models through three simulation scenarios comparing DNN, BNL, and binary mixed logit models (BXL), as well as one experiment comparing DNN to BNL, BXL, MNL, and mixed logit (MXL) in analyzing the choice of trip purposes based on the National Household Travel Survey 2017. The results indicate that DNN can be used for choice analysis beyond the current practice of demand forecasting because it has the inherent utility interpretation and the power of automatically learning utility specification. Our results suggest DNN outperforms BNL, BXL, MNL, and MXL models in both prediction and interpretation when the sample size is large (≥O(104)), the input dimension is high, or the true data generating process is complex, while performing worse when the opposite is true. DNN outperforms BNL and BXL in zero-one, log, and approximation losses for most of the experiments, and the larger sample size leads to greater incremental value of using DNN over classical discrete choice models. Overall, this study introduces the statistical learning theory as a new foundation for high-dimensional data, complex statistical models, and non-asymptotic data regimes in choice analysis, and the experiments show the effective prediction and interpretation of DNN for its applications to policy and behavioral analysis." @default.
• W3158002759 created "2021-05-10" @default.
• W3158002759 creator A5023905102 @default.
• W3158002759 creator A5027149232 @default.
• W3158002759 creator A5063355512 @default.
• W3158002759 creator A5087622413 @default.
• W3158002759 date "2021-06-01" @default.
• W3158002759 modified "2023-10-14" @default.
• W3158002759 title "Deep neural networks for choice analysis: A statistical learning theory perspective" @default.
• W3158002759 cites W1561572740 @default.
• W3158002759 cites W1827495041 @default.
• W3158002759 cites W1967444754 @default.
• W3158002759 cites W1975625812 @default.
• W3158002759 cites W1982032418 @default.
• W3158002759 cites W1987233492 @default.
• W3158002759 cites W1987832219 @default.
• W3158002759 cites W1988115241 @default.
• W3158002759 cites W1988942353 @default.
• W3158002759 cites W2008900804 @default.
• W3158002759 cites W2025720061 @default.
• W3158002759 cites W2037633404 @default.
• W3158002759 cites W2061162760 @default.
• W3158002759 cites W2064980505 @default.
• W3158002759 cites W2081762866 @default.
• W3158002759 cites W2084341220 @default.
• W3158002759 cites W2103496339 @default.
• W3158002759 cites W2137983211 @default.
• W3158002759 cites W2149298154 @default.
• W3158002759 cites W2159750996 @default.
• W3158002759 cites W2160607820 @default.
• W3158002759 cites W2163922914 @default.
• W3158002759 cites W2180559388 @default.
• W3158002759 cites W2550848904 @default.
• W3158002759 cites W2587802550 @default.
• W3158002759 cites W2593182953 @default.
• W3158002759 cites W2610886376 @default.
• W3158002759 cites W2657631929 @default.
• W3158002759 cites W2793820729 @default.
• W3158002759 cites W2889617671 @default.
• W3158002759 cites W2901371989 @default.
• W3158002759 cites W2919115771 @default.
• W3158002759 cites W2973461188 @default.
• W3158002759 cites W3004748517 @default.
• W3158002759 cites W3047663291 @default.
• W3158002759 cites W3122678879 @default.
• W3158002759 doi "https://doi.org/10.1016/j.trb.2021.03.011" @default.
• W3158002759 hasPublicationYear "2021" @default.
• W3158002759 type Work @default.
• W3158002759 sameAs 3158002759 @default.
• W3158002759 citedByCount "15" @default.
• W3158002759 countsByYear W31580027592021 @default.
• W3158002759 countsByYear W31580027592022 @default.
• W3158002759 countsByYear W31580027592023 @default.
• W3158002759 crossrefType "journal-article" @default.
• W3158002759 hasAuthorship W3158002759A5023905102 @default.
• W3158002759 hasAuthorship W3158002759A5027149232 @default.
• W3158002759 hasAuthorship W3158002759A5063355512 @default.
• W3158002759 hasAuthorship W3158002759A5087622413 @default.
• W3158002759 hasBestOaLocation W31580027592 @default.
• W3158002759 hasConcept C111472728 @default.
• W3158002759 hasConcept C117568660 @default.
• W3158002759 hasConcept C119857082 @default.
• W3158002759 hasConcept C126255220 @default.
• W3158002759 hasConcept C12713177 @default.
• W3158002759 hasConcept C138885662 @default.
• W3158002759 hasConcept C140331021 @default.
• W3158002759 hasConcept C149782125 @default.
• W3158002759 hasConcept C151956035 @default.
• W3158002759 hasConcept C154945302 @default.
• W3158002759 hasConcept C199360897 @default.
• W3158002759 hasConcept C202444582 @default.
• W3158002759 hasConcept C22019652 @default.
• W3158002759 hasConcept C2779530757 @default.
• W3158002759 hasConcept C2781067378 @default.
• W3158002759 hasConcept C33676613 @default.
• W3158002759 hasConcept C33923547 @default.
• W3158002759 hasConcept C41008148 @default.
• W3158002759 hasConcept C50644808 @default.
• W3158002759 hasConcept C527412718 @default.
• W3158002759 hasConcept C95057490 @default.
• W3158002759 hasConceptScore W3158002759C111472728 @default.
• W3158002759 hasConceptScore W3158002759C117568660 @default.
• W3158002759 hasConceptScore W3158002759C119857082 @default.
• W3158002759 hasConceptScore W3158002759C126255220 @default.
• W3158002759 hasConceptScore W3158002759C12713177 @default.
• W3158002759 hasConceptScore W3158002759C138885662 @default.
• W3158002759 hasConceptScore W3158002759C140331021 @default.
• W3158002759 hasConceptScore W3158002759C149782125 @default.
• W3158002759 hasConceptScore W3158002759C151956035 @default.
• W3158002759 hasConceptScore W3158002759C154945302 @default.
• W3158002759 hasConceptScore W3158002759C199360897 @default.
• W3158002759 hasConceptScore W3158002759C202444582 @default.
• W3158002759 hasConceptScore W3158002759C22019652 @default.
• W3158002759 hasConceptScore W3158002759C2779530757 @default.
• W3158002759 hasConceptScore W3158002759C2781067378 @default.
• W3158002759 hasConceptScore W3158002759C33676613 @default.
• W3158002759 hasConceptScore W3158002759C33923547 @default.
• W3158002759 hasConceptScore W3158002759C41008148 @default.

• next