{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/110643"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/110643","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Machine learning models for reliable airline ancillary pricing","abstract":"Machine learning is becoming increasingly prevalent for decision-making across key application areas such as healthcare, finance, law systems, and pricing. However, evaluating the predictive power of models on historical data is not enough. When deploying ML models in the real-world, system designers may wish that models exhibit certain properties which encourage trust, interpretability, and robustness. In this study, we discuss two such properties and demonstrate their relevance through experiments on an airline ancillary use-case. From a qualitative lens, designers may want the trained model to exhibit particular shape behavior that conforms to prior domain knowledge. Trends such as monotonicity, convexity, diminishing or accelerating returns are some of the desired shapes. Conformance to these shapes makes the model more interpretable for system designers, and adequately fair for customers. We notice that many such common shapes are related to derivatives, and propose a new approach, PenDer (Penalizing Derivatives), which incorporates these shape constraints by penalizing the derivatives. We further present an Augmented Lagrangian Method (ALM) to solve this constrained optimization problem. Experiments on three real-world datasets illustrate that even though both PenDer and state-of-the-art Lattice models achieve similar conformance to shape, PenDer captures better sensitivity of prediction with respect to intended features. We also demonstrate that PenDer achieves better test performance than Lattice while enforcing more desirable shape behavior. For the airline, PenDer appropriately balances the trade-off between constraint satisfaction and predictive performance -- leading to potential increased revenues compared to other models. Another important expectation of ML models is generalization to unseen data, that is, performance on new data. Textbook approaches assume that the data distribution at test-time is similar to the training distribution. In practice, however, this could be violated because of ever-changing customer behavior or a dynamic environment. Motivated by airlines' concerns of model performance drop during the COVID-19 pandemic, we study covariate shift to examine changes in the underlying data. We focus on shift detection before and during COVID-19 through a blend of (i) discriminative model training to distinguish train from test, and (ii) statistical testing of estimated feature densities. After experiments, we note that customer behavior has changed with notable changes being an increase in advance bookings, one-way trips, and individual travel compared to group travel. Presence of such drift indicates that the airline must perform correction before deployment for optimal performance.","abstract_html":"Machine learning is becoming increasingly prevalent for decision-making across key application areas such as healthcare, finance, law systems, and pricing. However, evaluating the predictive power of models on historical data is not enough. When deploying ML models in the real-world, system designers may wish that models exhibit certain properties which encourage trust, interpretability, and robustness. In this study, we discuss two such properties and demonstrate their relevance through experiments on an airline ancillary use-case. From a qualitative lens, designers may want the trained model to exhibit particular shape behavior that conforms to prior domain knowledge. Trends such as monotonicity, convexity, diminishing or accelerating returns are some of the desired shapes. Conformance to these shapes makes the model more interpretable for system designers, and adequately fair for customers. We notice that many such common shapes are related to derivatives, and propose a new approach, PenDer (Penalizing Derivatives), which incorporates these shape constraints by penalizing the derivatives. We further present an Augmented Lagrangian Method (ALM) to solve this constrained optimization problem. Experiments on three real-world datasets illustrate that even though both PenDer and state-of-the-art Lattice models achieve similar conformance to shape, PenDer captures better sensitivity of prediction with respect to intended features. We also demonstrate that PenDer achieves better test performance than Lattice while enforcing more desirable shape behavior. For the airline, PenDer appropriately balances the trade-off between constraint satisfaction and predictive performance -- leading to potential increased revenues compared to other models. Another important expectation of ML models is generalization to unseen data, that is, performance on new data. Textbook approaches assume that the data distribution at test-time is similar to the training distribution. In practice, however, this could be violated because of ever-changing customer behavior or a dynamic environment. Motivated by airlines' concerns of model performance drop during the COVID-19 pandemic, we study covariate shift to examine changes in the underlying data. We focus on shift detection before and during COVID-19 through a blend of (i) discriminative model training to distinguish train from test, and (ii) statistical testing of estimated feature densities. After experiments, we note that customer behavior has changed with notable changes being an increase in advance bookings, one-way trips, and individual travel compared to group travel. Presence of such drift indicates that the airline must perform correction before deployment for optimal performance.","abstract_has_math":false,"creators":["Gupta, Akhil"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Industrial Engineering","degree_department":null,"school":null,"contributors":["Marla, Lavanya"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2021,"date_issued":"2021-09-17T02:34:20Z","date_published":"2021-09-17T02:34:20Z","updated_at":"2026-07-22T22:24:52Z","subjects":["Machine Learning","Pricing","Airline Ancillary","Neural Networks"],"languages":["en"],"rights":["Copyright 2021 Akhil Gupta"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/110643","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Marla, Lavanya"]},{"key":"dc:creator","label":"Author","values":["Gupta, Akhil"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2021-09-17T02:34:20Z","2023-09-17T02:34:57Z","2021-04-27","2021-05"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Industrial Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Machine Learning","Pricing","Airline Ancillary","Neural Networks"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2021 Akhil Gupta"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/110643"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Machine learning is becoming increasingly prevalent for decision-making across key application areas such as healthcare, finance, law systems, and pricing. However, evaluating the predictive power of models on historical data is not enough. When deploying ML models in the real-world, system designers may wish that models exhibit certain properties which encourage trust, interpretability, and robustness. In this study, we discuss two such properties and demonstrate their relevance through experiments on an airline ancillary use-case. From a qualitative lens, designers may want the trained model to exhibit particular shape behavior that conforms to prior domain knowledge. Trends such as monotonicity, convexity, diminishing or accelerating returns are some of the desired shapes. Conformance to these shapes makes the model more interpretable for system designers, and adequately fair for customers. We notice that many such common shapes are related to derivatives, and propose a new approach, PenDer (Penalizing Derivatives), which incorporates these shape constraints by penalizing the derivatives. We further present an Augmented Lagrangian Method (ALM) to solve this constrained optimization problem. Experiments on three real-world datasets illustrate that even though both PenDer and state-of-the-art Lattice models achieve similar conformance to shape, PenDer captures better sensitivity of prediction with respect to intended features. We also demonstrate that PenDer achieves better test performance than Lattice while enforcing more desirable shape behavior. For the airline, PenDer appropriately balances the trade-off between constraint satisfaction and predictive performance -- leading to potential increased revenues compared to other models. Another important expectation of ML models is generalization to unseen data, that is, performance on new data. Textbook approaches assume that the data distribution at test-time is similar to the training distribution. In practice, however, this could be violated because of ever-changing customer behavior or a dynamic environment. Motivated by airlines' concerns of model performance drop during the COVID-19 pandemic, we study covariate shift to examine changes in the underlying data. We focus on shift detection before and during COVID-19 through a blend of (i) discriminative model training to distinguish train from test, and (ii) statistical testing of estimated feature densities. After experiments, we note that customer behavior has changed with notable changes being an increase in advance bookings, one-way trips, and individual travel compared to group travel. Presence of such drift indicates that the airline must perform correction before deployment for optimal performance.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2023-05-01","The student, Akhil Gupta, accepted the attached license on 2021-04-26 at 11:44.","The student, Akhil Gupta, submitted this Thesis for approval on 2021-04-26 at 12:04.","This Thesis was approved for publication on 2021-04-27 at 10:29.","DSpace SAF Submission Ingestion Package generated from Vireo submission #16241 on 2021-09-16 at 17:02:34","Made available in DSpace on 2021-09-17T02:34:20Z (GMT). No. of bitstreams: 3 GUPTA-THESIS-2021.pdf: 8270332 bytes, checksum: ee5c4e8dc172d2bcb79bc0782392619b (MD5) Thesis_AG.zip: 6639131 bytes, checksum: 302e0eec54817530d5854d184e7a622d (MD5) LICENSE.txt: 4208 bytes, checksum: b2f26da3e8ab0f86f6e22a2c27d408e6 (MD5) Previous issue date: 2021-04-27","Embargo set by: Seth Robbins for item 118486 Lift date: 2023-09-17T02:34:57Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Machine learning models for reliable airline ancillary pricing"]}]}],"canonical_facts":{"dc:contributor":["Marla, Lavanya"],"dc:creator":["Gupta, Akhil"],"dc:date":["2021-09-17T02:34:20Z","2023-09-17T02:34:57Z","2021-04-27","2021-05"],"dc:description":["Machine learning is becoming increasingly prevalent for decision-making across key application areas such as healthcare, finance, law systems, and pricing. However, evaluating the predictive power of models on historical data is not enough. When deploying ML models in the real-world, system designers may wish that models exhibit certain properties which encourage trust, interpretability, and robustness. In this study, we discuss two such properties and demonstrate their relevance through experiments on an airline ancillary use-case. From a qualitative lens, designers may want the trained model to exhibit particular shape behavior that conforms to prior domain knowledge. Trends such as monotonicity, convexity, diminishing or accelerating returns are some of the desired shapes. Conformance to these shapes makes the model more interpretable for system designers, and adequately fair for customers. We notice that many such common shapes are related to derivatives, and propose a new approach, PenDer (Penalizing Derivatives), which incorporates these shape constraints by penalizing the derivatives. We further present an Augmented Lagrangian Method (ALM) to solve this constrained optimization problem. Experiments on three real-world datasets illustrate that even though both PenDer and state-of-the-art Lattice models achieve similar conformance to shape, PenDer captures better sensitivity of prediction with respect to intended features. We also demonstrate that PenDer achieves better test performance than Lattice while enforcing more desirable shape behavior. For the airline, PenDer appropriately balances the trade-off between constraint satisfaction and predictive performance -- leading to potential increased revenues compared to other models. Another important expectation of ML models is generalization to unseen data, that is, performance on new data. Textbook approaches assume that the data distribution at test-time is similar to the training distribution. In practice, however, this could be violated because of ever-changing customer behavior or a dynamic environment. Motivated by airlines' concerns of model performance drop during the COVID-19 pandemic, we study covariate shift to examine changes in the underlying data. We focus on shift detection before and during COVID-19 through a blend of (i) discriminative model training to distinguish train from test, and (ii) statistical testing of estimated feature densities. After experiments, we note that customer behavior has changed with notable changes being an increase in advance bookings, one-way trips, and individual travel compared to group travel. Presence of such drift indicates that the airline must perform correction before deployment for optimal performance.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2023-05-01","The student, Akhil Gupta, accepted the attached license on 2021-04-26 at 11:44.","The student, Akhil Gupta, submitted this Thesis for approval on 2021-04-26 at 12:04.","This Thesis was approved for publication on 2021-04-27 at 10:29.","DSpace SAF Submission Ingestion Package generated from Vireo submission #16241 on 2021-09-16 at 17:02:34","Made available in DSpace on 2021-09-17T02:34:20Z (GMT). No. of bitstreams: 3 GUPTA-THESIS-2021.pdf: 8270332 bytes, checksum: ee5c4e8dc172d2bcb79bc0782392619b (MD5) Thesis_AG.zip: 6639131 bytes, checksum: 302e0eec54817530d5854d184e7a622d (MD5) LICENSE.txt: 4208 bytes, checksum: b2f26da3e8ab0f86f6e22a2c27d408e6 (MD5) Previous issue date: 2021-04-27","Embargo set by: Seth Robbins for item 118486 Lift date: 2023-09-17T02:34:57Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/110643"],"dc:language":["en"],"dc:rights":["Copyright 2021 Akhil Gupta"],"dc:subject":["Machine Learning","Pricing","Airline Ancillary","Neural Networks"],"dc:title":["Machine learning models for reliable airline ancillary pricing"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Industrial Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:52Z"}