A new recommendation system on the basis of consumer initiative decision based on an associative classification approach
| Published date | 05 February 2018 |
| Date | 05 February 2018 |
| Pages | 188-203 |
| DOI | https://doi.org/10.1108/IMDS-02-2017-0057 |
| Author | Chengxin Yin,Yan Guo,Jianguo Yang,Xiaoting Ren |
| Subject Matter | Information & knowledge management,Information systems,Data management systems,Knowledge management,Knowledge sharing,Management science & operations,Supply chain management,Supply chain information systems,Logistics,Quality management/systems |
A new recommendation system on
the basis of consumer initiative
decision based on an associative
classification approach
Chengxin Yin and Yan Guo
Chengdu University of Technology, Chengdu, China
Jianguo Yang
Chengdu Aeronautic Polytechnic, Chengdu, China, and
Xiaoting Ren
China University of Mining and Technology, Xuzhou, China
Abstract
Purpose –The purpose of this paper is to improve the customer satisfaction by offering online personalized
recommendation system.
Design/methodology/approach –By employing an innovative associative classification method, this
paper is able to predict a customer’s pleasure during the online while-recommending process. Consumers can
make an active decision to recommended products. Based on customer’s characteristics, a product will
be recommended to the potential buyer if the model predicts that he/she will click to view the product. That is,
he/she is satisfied with the recommended product. Finally, the feasibility of the proposed recommendation
system is validated through a Taobao shop.
Findings –The results of the experimental study clearly show that the online personalized recommendation
system maximizes the customer’s satisfaction during the online while-recommending process based on an
innovative associative classification method on the basis of consumer initiative decision.
Originality/value –Conventionally, customers are considered as passive recipients of the recommendation
system. However, customers are tired of the recommendation system, and they can do nothing
sometimes. This paper designs a new recommendation system on the basis of consumer initiative decision.
The proposed recommendat ion system maximizes the cus tomer’s satisfaction dur ing the online
while-recommending process.
Keywords Electronic commerce, Customer satisfaction, Recommendation system, Initiative decision
Paper type Research paper
1. Introduction
The rapid development of e-commerceand increasingly massiveinformation have caused that
consumers cannotquickly find their own interestsand needed products (Kemény et al., 2016).
Electronic commerce recommendation system is an efficient way to solve the problem of
information overload. The research of recommendation system is a part of the automation
research of personalized website and widely used by e-commerce practitioners (Hung, 2005;
Guo et al., 2017). Recommendation systems recommend the information and products to
customers based on their interests, characteristics and purchasing behavior, which can
effectively increase sales (Bodapati, 2008). They also provide an effective way for enterprise
managers to analyze consumers’behavior, predict product sales and make better decisions
(Punj and Moore,2007; Li et al., 2017b). Therefore,the recommendation system is becomingan
increasingly hot research spot.
Existing research on the recommendation system has emerged a large number of
outstanding results (Nilashi et al., 2015). Some scholars from the technical level enhance the
recommendation efficiency through the improvement of the speed and accuracy of
recommendation algorithm (Lee et al., 2016; Guo et al., 2017). Other scholars start from
Industrial Management & Data
Systems
Vol. 118 No. 1, 2018
pp. 188-203
© Emerald PublishingLimited
0263-5577
DOI 10.1108/IMDS-02-2017-0057
Received 13 February 2017
Revised 22 June 2017
Accepted 28 July 2017
The current issue and full text archive of this journal is available on Emerald Insight at:
www.emeraldinsight.com/0263-5577.htm
188
IMDS
118,1
customers’point of view and aim to the accuracy through various ways, for example
analyzing customer’s prior online behavior and presenting information on products to
match customer’s preference (Kim, 2011; Li et al., 2017a). However, most consumers are only
passive recipients of the recommended system from the research field of consumer behavior.
They do not really experience the role of the recommendation system as a purchase decision
aid, which affects the consumer’s willingness to use the recommended system. Even
consumers are very disgusted with the recommendation system because of the forced
nature of advertising push. Let us consider a case below.
Lily is in need of a baby carriage as a gift for her friend. She visits online stores to look
for information and compares the prices online with the ones in physical store. Eventually,
she chooses the physical store through comprehensive consideration in terms of the freight,
product quality and other reasons. However, after the last web browsing, Lily receives a
large number of recommended information about baby cars and related products.
The information not only appears in the recommendation system of shopping site itself, also
in social network and other website. It makes her very tired, especially when the others see
the information. People always guess why this information appears in front of her, whether
she is pregnant, etc. It turns out that Lily is not content with the recommended procedure.
This exemplifies the case that a customer may receive recommended information, but the
recommendation system is not successful in pleasing the customer. Consumers are only
passive to receive information which is not what they need. Only when customers claim that
the information makes them happy journey, can they claim that the system has made
effective recommendations. Therefore, we must consider consumer satisfaction during the
online while-recommending process and c ustomer’s decision making in designing
recommendation systems, and make it different from other previous studies,
which evaluate the success of the recommendation system after the end of consumer
shopping ( Jiang et al., 2010).
How can a customer’s satisfaction with a specific product be measured and attained in
the process of buying goods? The rapid development of e-commerce affords us an
opportunity to predict customers’reactions after they accept the recommended products.
Many online stores, such as Amazon.com and Tao.com can collect consumers’online
behavior data. The information is then often used to support a firm’s product strategy and
customer relationship management ( Jiang et al., 2015; Li et al., 2017a). Customers’feedback
on online recommendations reflects their needs, preferences, personal profile and voices
their opinions about the recommendation as average or satisfaction. We usually think that if
consumers are satisfied with the recommended products, they will click to view details.
Average means they will click on the “exchange for a change”to see other products.
However, two cases have not yet been considered. One is that consumers do not make any
response to the recommended products. In the past, we have not made a further analysis of
this type of consumers, so that e-tailers ignore their true feelings about the recommendation
system. The other is that consumers, as passive recipients of information, cannot refuse
recommended products appearing in front of them, which cannot express their aversion
to recommended products. These two cases are barriers to consumer satisfaction in the
recommendation process.
This research proposes an evaluation classification model to estimate a potential
customer’s satisfaction level. We put forward that consumers can turn into active
participants rather than passive recipients. Consumers can click “reject”to express their
disgust. From consumer behavior analysis, it is easy to obtain personalized information and
customers’after-accept satisfaction level of the recommended products. Using personal
information and responses, the online store can more accurately predict customers’true
sentiments toward a recommended product, and recommend a more suitable product for
the potential customer to enjoy. Then, the paper builds an evaluation classifier for a product
189
Consumer
initiative
decision
To continue reading
Request your trial