TY - JOUR
T1 - Multiple resource allocation for precision marketing
AU - Zhang, Siyu
AU - Liao, Peng
AU - Ye, Heng Qing
AU - Zhou, Zhili
N1 - Funding Information:
This work was supported by the National Natural Science Foundation of China (NSFC) [Grant No: 71971168].
Publisher Copyright:
© Published under licence by IOP Publishing Ltd.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020/9/18
Y1 - 2020/9/18
N2 - In the precision marketing of a new product, it is a challenge to allocate limited resources to the target customer groups with different characteristics. We presented a framework using distance-based algorithm, K-Nearest-Neighbour, and support vector machine to capture customers' preference towards promotion channel. Additionally, on-line learning programming was combined with machine learning strategies to fit a dynamic environment, evaluating its performance through a parsimonious model of minimum regret. A resource optimization model was proposed using classification results as input. In particular, we collected data from a loan agency that offers loans to small business merchants. Our sample contained 525,919 customers who will be introduced to a new financial product. By simulating different scenarios between resources and demand, we showed an up to 22.42% increase in the number of expected merchants when K-NN was performed with optimal resource allocation strategy. Our results also show that K-NN is the most stable method to perform classification, and that distance-based algorithm has the most efficient adoption with on-line learning.
AB - In the precision marketing of a new product, it is a challenge to allocate limited resources to the target customer groups with different characteristics. We presented a framework using distance-based algorithm, K-Nearest-Neighbour, and support vector machine to capture customers' preference towards promotion channel. Additionally, on-line learning programming was combined with machine learning strategies to fit a dynamic environment, evaluating its performance through a parsimonious model of minimum regret. A resource optimization model was proposed using classification results as input. In particular, we collected data from a loan agency that offers loans to small business merchants. Our sample contained 525,919 customers who will be introduced to a new financial product. By simulating different scenarios between resources and demand, we showed an up to 22.42% increase in the number of expected merchants when K-NN was performed with optimal resource allocation strategy. Our results also show that K-NN is the most stable method to perform classification, and that distance-based algorithm has the most efficient adoption with on-line learning.
UR - http://www.scopus.com/inward/record.url?scp=85092540109&partnerID=8YFLogxK
U2 - 10.1088/1742-6596/1592/1/012034
DO - 10.1088/1742-6596/1592/1/012034
M3 - Conference article
AN - SCOPUS:85092540109
SN - 1742-6588
VL - 1592
JO - Journal of Physics: Conference Series
JF - Journal of Physics: Conference Series
IS - 1
M1 - 012034
T2 - 3rd International Conference on Physics, Mathematics and Statistics, ICPMS 2020
Y2 - 20 May 2020 through 22 May 2020
ER -