2026-09-20T10:22:29Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1567992024-09-17T03:02:09Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Perakis, Georgia
Hensgen, Michael Lowell
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2024-09-16T13:49:59Z
2024-09-16T13:49:59Z
2024-05
2024-07-11T14:37:01.788Z
https://hdl.handle.net/1721.1/156799
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.
M.Eng.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright retained by author(s)
https://rightsstatements.org/page/InC-EDU/1.0/
Coherency Loss for Hierarchical Time Series Forecasting
Thesis
application/pdf
Master
Master of Engineering in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="f26d5282-3466-4461-b9ec-4eec4d215fe6">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Coherency Loss for Hierarchical Time Series Forecasting</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2024-05</PublicationDate>
<Authors>
<Author>
<DisplayName>Hensgen, Michael Lowell</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://rightsstatements.org/page/InC-EDU/1.0/</License>
<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>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>