{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/156799"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/156799","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Coherency Loss for Hierarchical Time Series Forecasting","abstract":"In hierarchical time series forecasting, some series are aggregated from others, producing a known coherency metric between series. We present a new method for enforcing coherency on hierarchical time series forecasts. We propose a new loss function, called Network Coherency Loss, that minimizes the coherency loss of the weight and bias of the final linear layer of a neural network. We compare it against a baseline without coherency and a state of the art method that uses projection to strictly enforce coherency. We find that, by choosing our Network Coherency Loss parameters based on validation data, for four datasets of varying sizes we produce improved accuracy over our two benchmark models. We also find that, when compared to an alternative loss function also designed to produce coherency, our Network Coherency Loss function produces similar accuracies but improves the coherency on the test data.","abstract_html":"In hierarchical time series forecasting, some series are aggregated from others, producing a known coherency metric between series. We present a new method for enforcing coherency on hierarchical time series forecasts. We propose a new loss function, called Network Coherency Loss, that minimizes the coherency loss of the weight and bias of the final linear layer of a neural network. We compare it against a baseline without coherency and a state of the art method that uses projection to strictly enforce coherency. We find that, by choosing our Network Coherency Loss parameters based on validation data, for four datasets of varying sizes we produce improved accuracy over our two benchmark models. We also find that, when compared to an alternative loss function also designed to produce coherency, our Network Coherency Loss function produces similar accuracies but improves the coherency on the test data.","abstract_has_math":false,"creators":["Hensgen, Michael Lowell"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Perakis, Georgia"],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-05","date_published":"2024-05","updated_at":"2026-07-22T22:22:26Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"rights_urls":["https://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/156799","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Perakis, Georgia"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Hensgen, Michael Lowell"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-09-16T13:49:59Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-09-16T13:49:59Z"]},{"key":"dc:date.issued","label":"Date","values":["2024-05"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/156799"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["In hierarchical time series forecasting, some series are aggregated from others, producing a known coherency metric between series. We present a new method for enforcing coherency on hierarchical time series forecasts. We propose a new loss function, called Network Coherency Loss, that minimizes the coherency loss of the weight and bias of the final linear layer of a neural network. We compare it against a baseline without coherency and a state of the art method that uses projection to strictly enforce coherency. We find that, by choosing our Network Coherency Loss parameters based on validation data, for four datasets of varying sizes we produce improved accuracy over our two benchmark models. We also find that, when compared to an alternative loss function also designed to produce coherency, our Network Coherency Loss function produces similar accuracies but improves the coherency on the test data."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Coherency Loss for Hierarchical Time Series Forecasting"]}]}],"canonical_facts":{"dc:contributor.advisor":["Perakis, Georgia"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Hensgen, Michael Lowell"],"dc:date.accessioned":["2024-09-16T13:49:59Z"],"dc:date.available":["2024-09-16T13:49:59Z"],"dc:date.issued":["2024-05"],"dc:description.abstract":["In hierarchical time series forecasting, some series are aggregated from others, producing a known coherency metric between series. We present a new method for enforcing coherency on hierarchical time series forecasts. We propose a new loss function, called Network Coherency Loss, that minimizes the coherency loss of the weight and bias of the final linear layer of a neural network. We compare it against a baseline without coherency and a state of the art method that uses projection to strictly enforce coherency. We find that, by choosing our Network Coherency Loss parameters based on validation data, for four datasets of varying sizes we produce improved accuracy over our two benchmark models. We also find that, when compared to an alternative loss function also designed to produce coherency, our Network Coherency Loss function produces similar accuracies but improves the coherency on the test data."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/156799"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"dc:rights.uri":["https://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Coherency Loss for Hierarchical Time Series Forecasting"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:22:26Z"}