2026-09-18T19:13:15Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/998062026-06-06T01:03:18Zcom_1721.1_7582com_1721.1_7581com_1721.1_101402col_1721.1_131023col_1721.1_101610
Roberto Perez-Franco.
Bulusu, Vinod
Kim, Haekyun
Massachusetts Institute of Technology. Engineering Systems Division.
Massachusetts Institute of Technology. Engineering Systems Division
2015-11-09T19:50:04Z
2015-11-09T19:50:04Z
2015
2015
http://hdl.handle.net/1721.1/99806
927169170
Thesis: M. Eng. in Logistics, Massachusetts Institute of Technology, Engineering Systems Division, 2015.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 54-55).
Improvement in sales forecasting allows firms not only to respond quickly to customers' needs but also to reduce inventory costs, ultimately increasing their profits. Sales forecasts have been studied extensively to improve their accuracy in many different fields. However, for automotive batteries, it is very difficult to develop a highly accurate forecast model because many variables need to be considered and their correlations are complex. Additionally, current sales forecasts are derived from historical data and thus do not include any other causal factor analysis. In this study we applied causal factor analysis to determine how the forecast accuracy could be improved. We focused on understanding the relationship between temperature and sales. Using regression modelling, we found that there is a quadratic relationship between temperature and battery sales. We validated the model by comparing the actual and predicted sales for various geographies and times. We concluded that the model is more robust for predicting sales across various times than through various geographies.
by Vinod Bulusu and Haekyun Kim.
M.Eng. in Logistics
55 pages
eng
Massachusetts Institute of Technology
M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission.
http://dspace.mit.edu/handle/1721.1/7582
Engineering Systems Division.
Improving automotive battery sales forecast
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="099cfd69-6260-4ff0-bdc0-5cfd9cdd7b4f">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Improving automotive battery sales forecast</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2015</PublicationDate>
<Authors>
<Author>
<DisplayName>Bulusu, Vinod</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
<Author>
<DisplayName>Kim, Haekyun</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Engineering Systems Division.</Keyword>
<Abstract>Improvement in sales forecasting allows firms not only to respond quickly to customers' needs but also to reduce inventory costs, ultimately increasing their profits. Sales forecasts have been studied extensively to improve their accuracy in many different fields. However, for automotive batteries, it is very difficult to develop a highly accurate forecast model because many variables need to be considered and their correlations are complex. Additionally, current sales forecasts are derived from historical data and thus do not include any other causal factor analysis. In this study we applied causal factor analysis to determine how the forecast accuracy could be improved. We focused on understanding the relationship between temperature and sales. Using regression modelling, we found that there is a quadratic relationship between temperature and battery sales. We validated the model by comparing the actual and predicted sales for various geographies and times. We concluded that the model is more robust for predicting sales across various times than through various geographies.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>