A grocery recommendation for off-line shoppers
| Pages | 468-481 |
| DOI | https://doi.org/10.1108/OIR-04-2016-0104 |
| Date | 13 August 2018 |
| Published date | 13 August 2018 |
| Author | Jae Kyeong Kim,Hyun Sil Moon,Byong Ju An,Il Young Choi |
| Subject Matter | Library & information science,Information behaviour & retrieval,Collection building & management,Bibliometrics,Databases,Information & knowledge management,Information & communications technology,Internet,Records management & preservation,Document management |
A grocery recommendation
for off-line shoppers
Jae Kyeong Kim and Hyun Sil Moon
School of Management, Kyunghee University, Seoul, Republic of Korea
Byong Ju An
School of Dance, Kyunghee University, Seoul, Republic of Korea, and
Il Young Choi
Kyunghee University, Seoul, Republic of Korea
Abstract
Purpose –Many off-line retailers have experienced a slump in sales and have the potential risk of overstock
or understock. To overcome these problems, retailers have applied data mining techniques, such as
association rule mining or sequential association rule mining, to increase sales and predict product demand.
However, because these techniques cannot generate shopper-centric rules, many off-line shoppers are often
inconvenienced after writing their shopping lists carefully and comprehensively. Therefore, the purpose of
this paper is to propose a personalized recommendation methodology for off-line grocery shoppers.
Design/methodology/approach –This paper employs a Markov chain model to generate recommendations
for the shopper’s next shopping basket. The proposed methodology is based on the knowledge of both purchased
products and purchase sequences. This paper compares the proposed methodology with a traditional collaborative
filtering (CF)-based system, a bestseller-based system and a Markov-chain-based system as benchmark systems.
Findings –The proposed methodology achieves improvements of 15.87, 14.06 and 37.74 percent with respect
to the CF-, Markov chain-, and best-seller-based benchmark systems, respectively, meaning that not only the
purchased products but also the purchase sequences are important elements in the personalizationof grocery
recommendations.
Originality/value –Most of the previous studies on this topic have proposed on-line recommendation
methodologies. However, because off-line stores collect transaction data from point-of-sale devices, this
research proposes a methodology based on purchased products and purchase patterns for off-line grocery
recommendations. In practice, this study implies that both purchased products and purchase sequences are
viable elements in off-line grocery recommendations.
Keywords Markov chain, Personalization, Off-line grocery recommender system,
Next-basket recommendation
Paper type Research paper
1. Introduction
Grocery stores are indispensable resources because they sell daily necessities, such as meat,
fruits, vegetables, seafood and other commodities. However, grocery shopping is regarded
as a routine and trivial task (Lang and Hooker, 2013; Machleit and Eroglu, 2000), and
decision-makingwithregardtothistaskishabitual(Eastet al., 1994; Iyer and Ahlawat, 1987;
Nordfalt, 2009). In other words, because grocery shopping is regarded as a low-involvement
activity (Beharrell and Denison, 1995; Houston and Rothschild, 1977; Lastovicka and Gardner,
1978; Winter and Rossiter, 1989), it is characterized by low brand loyalty, low switching costs,
and little information-seeking behavior.
Recently, many traditional grocery stores have experienced a slump in sales (Kriel, 2015)
because they have faced fierce competition from on-line retail stores. Furthermore, grocery
stores have the potential risk of overstock or understock due to demand uncertainty
(Roy et al., 2018). To overcome these circumstances, grocery stores haveadopted data mining
techniques,such as association rule mining andsequential association rule mining, to provide
personalized recommendations and to forecast the demand for products (Bala, 2012;
Hipp et al., 2000; Pasquier et al.,1999;Riazet al., 2014; Shim et al., 2012). However, such data
mining techniques cannot generate shopper-specific rules (Yap et al., 2012).
Online Information Review
Vol. 42 No. 4, 2018
pp. 468-481
© Emerald PublishingLimited
1468-4527
DOI 10.1108/OIR-04-2016-0104
Received 8 April 2016
Revised 6 January 2017
5 May 2017
Accepted 2 October 2017
The current issue and full text archive of this journal is available on Emerald Insight at:
www.emeraldinsight.com/1468-4527.htm
468
OIR
42,4
To continue reading
Request your trial