Customer Behaviour Analysis for Recommendation of Supermarket Ware
In this paper, we present a prediction model based on the behaviour of each customer using data mining techniques. The proposed model utilizes a supermarket database and an additional database from Amazon Company, both containing information about custome
- PDF / 652,153 Bytes
- 10 Pages / 439.37 x 666.142 pts Page_size
- 96 Downloads / 190 Views
Abstract. In this paper, we present a prediction model based on the behaviour of each customer using data mining techniques. The proposed model utilizes a supermarket database and an additional database from Amazon Company, both containing information about customers’ purchases. Subsequently, our model analyzes these data in order to classify customers as well as products; whereas being trained and validated with real data. This model is targeted towards classifying customers according to their consuming behaviour and consequently propose new products more likely to be purchased by them. The corresponding prediction model is intended to be utilized as a tool for marketers so as to provide an analytically targeted and specified consumer behavior. Keywords: Supervised learning · Data analytics · Customer behaviour · Knowledge extraction · Personalization · Recommendation system
1
Introduction
During the last years, more and more companies store their data into large data-centers so as to initially analyze them and to further understand how their consumers behave. Every day, a large amount of information is accessed and processed by companies in order to get a deeper knowledge about their products’ sales and consumers’ purchases. From small shops to large enterprises, owners try to record information that probably contains useful data regarding consumers. In addition, the rapid development of technology provides high quality network services. A large percentage of users utilize the Internet for information of each field. For this reason, companies try to take advantage of this situation by creating systems that store information about users who entered their site in order to provide them with personalized promotions. Companies concentrate on their desired information and personal transactions. Businesses provide their customers with cards so they can record every buying detail. This procedure has led to a huge amount of data and search methods for data processing. Historically, several analysts have been involved in the collection and processing of data. In modern times, the data volume is so huge that it requires the use c IFIP International Federation for Information Processing 2016 Published by Springer International Publishing Switzerland 2016. All Rights Reserved L. Iliadis and I. Maglogiannis (Eds.): AIAI 2016, IFIP AICT 475, pp. 471–480, 2016. DOI: 10.1007/978-3-319-44944-9 41
472
S.A. Iakovou et al.
of specific methods so as to enable analysts to export correct conclusions. Due to the increased volume for automatic data analysis, methods use complex tools; along with the help of modern technologies, data collection can be now considered as a simple process. Analyzing a dataset is a key aspect to understanding how customers think and behave during each specific period of the year. There are many classification and clustering methods which can be successfully used by analysts to aid them broach in consumers’ mind. More specifically, supervised machine learning techniques are utilized in the present manuscript
Data Loading...
