TY - GEN
T1 - Retail Promotion Forecasting
T2 - IFIP WG 5.7 International Conference, APMS 2019
AU - Bojer, Casper Solheim
AU - Dukovska-Popovska, Iskra
AU - Christensen, Flemming Max Møller
AU - Steger-Jensen, Kenn
PY - 2019
Y1 - 2019
N2 - Promotions at retailers are an effective marketing instrument, driving customers to stores, but their demand is particularly challenging to forecast due to limited historical data. Previous studies have proposed and evaluated different promotion forecasting methods at product level, such as linear regression methods and random trees. However, there is a lack of unified overview of the performance of the different methods due to differences in modeling choices and evaluation conditions across the literature. This paper adds to the methods the class of emerging techniques, based on ensembles of decision trees, and provides a comprehensive comparison of different methods on data from a Danish discount grocery chain for forecasting chain-level daily product demand during promotions with a four-week horizon. The evaluation shows that ensembles of decision trees are more accurate than methods such as penalized linear regression and regression trees, and that the ensembles of decision trees benefit from pooling and feature engineering.
AB - Promotions at retailers are an effective marketing instrument, driving customers to stores, but their demand is particularly challenging to forecast due to limited historical data. Previous studies have proposed and evaluated different promotion forecasting methods at product level, such as linear regression methods and random trees. However, there is a lack of unified overview of the performance of the different methods due to differences in modeling choices and evaluation conditions across the literature. This paper adds to the methods the class of emerging techniques, based on ensembles of decision trees, and provides a comprehensive comparison of different methods on data from a Danish discount grocery chain for forecasting chain-level daily product demand during promotions with a four-week horizon. The evaluation shows that ensembles of decision trees are more accurate than methods such as penalized linear regression and regression trees, and that the ensembles of decision trees benefit from pooling and feature engineering.
KW - Grocery retail
KW - Machine learning
KW - Promotion forecasting
UR - http://www.scopus.com/inward/record.url?scp=85072984092&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-29996-5_66
DO - 10.1007/978-3-030-29996-5_66
M3 - Article in proceeding
SN - 978-3-030-29995-8
VL - 2
T3 - IFIP AICT - Advances in Information and Communication technology
SP - 575
EP - 582
BT - Advances in Production Management Systems. Towards Smart Production Management Systems
A2 - Ameri, Farhad
A2 - Stecke, Kathryn E.
A2 - von Cieminski, Gregor
A2 - Kiritsis, Dimitris
PB - Springer
Y2 - 1 September 2019 through 5 September 2019
ER -