Retrieval Number: B2290078219/19©BEIESP DOI: 10.35940/ijrte.B2290.078219 International Journal of Recent Technology and Engineering (IJRTE) ISSN: 2277-3878, Volume-8 Issue-2, July 2019 6198 Published By: Blue Eyes Intelligence Engineering & Sciences Publication Abstract: Recently, manufacturing industry faces lots of problem in predicting the customer behavior and group for matching their outcome with the profit. The organizations are finding difficult in identifying the customer behavior for the purpose of predicting the product design so as to increase the profit. The prediction of customer group is a challenging task for all the organization due to the current growing entrepreneurs. This results in using the machine learning algorithms to cluster the customer group for predicting the demand of the customers. This helps in decision making process of manufacturing the products. This paper attempts to predict the customer group for the wine data set extracted from UCI Machine Learning repository. The wine data set is subjected to dimensionality reduction with principal component analysis and linear discriminant analysis. A Performance analysis is done with various classification algorithms and comparative study is done with the performance metric such as accuracy, precision, recall, and f-score. Experimental results shows that after applying dimensionality reduction, the 2 component LDA reduced wine data set with the kernel SVM, Random Forest classifier is found to be effective with the accuracy of 100% compared to other classifiers. Index Terms: Machine Learning, Churn, Classification, accuracy, precision, recall, log loss and f-score. I. INTRODUCTION Customer group and segment analysis is directly connected with the financial profit of the company. So prediction of customer group have direct impact on the total revenue of the company and it is greatly found to be difficult task for each organization. Once the company identifies the customer group, then they can decide the product design and confirm the number of products to be manufactured based on the customer needs and expectation. The successful sales of any product is decided based on the prediction of the customer expectation and the level of customers. With the growth in the online shopping and offline shopping, the organization have lot of sources to predict the customer group. Customers are rapidly growing for the purchase of various wine brands in supermarkets, five star restaurants, wine shops, online shopping portal and mobile shopping. The Revised Manuscript Received on July 20, 2019. R. Suguna, Professor, Computer Science and Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, Chennai, TamilNadu, India. M. Shyamala Devi, Associate Professor, Computer Science and Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, Chennai, TamilNadu, India. Rincy Merlin Mathew, Lecturer, Department of Computer Science, College of Science and Arts, Khamis Mushayt, King Khalid university, Abha, Asir, Saudi Arabia. organization also need to maintain the customer loyalty while designing the product. The paper is organized in such a way that Section 2 deals with the related works. Section 3 discuss about the proposed work followed by the implementation and Performance Analysis in Section 4. The paper is concluded with Section 5. II. RELATED WORK A. Literature Review In the process of wine production it is necessary to analyses the influence of chemical samples to taste. The analysis indirectly helps in changes in proportion during wine preparation and predicts its demand in market. The association of chemical parameters can revealed by data mining algorithms. Suitable models can be built to determine the combination of chemical parameters for better wine production. Techniques such as Linear Regression, Decision Trees and Artificial Neural Networks have been used to predict the organoleptic parameters [1]. Results state that accuracy level of built model is appreciable. An elaborate comparison on customer behavior predicted focusing on customer relationship management, approaches and datasets [2]. Studies reveal that compared to statistical methods, data mining techniques perform well in predictions. Among the data mining techniques, Artificial Neural Networks has been proved outperforming. The consumption rate of wine was assessed using parameters such as product involvement, subjective knowledge, personal traits and socio demographics. It was found that though it was expensive, the quality of wine rewarded the business [3]. Nowadays the sales of wine increase in online compared to outlets. To better understand the buying behavior a stimulus-response model was built to anticipate the sales rate [4]. The brands of wine has tremendous improvement and the market is highly competitive. Structural Equation modelling was developed to assess the models of wine brand and it was stated that wine experience is related its brand [5]. An online survey on relation between wine attributes and behavioral intentions was carried over and the responses are analyzed using hierarchical regression analysis. Results state that the factors influencing trust and taste impacts consumer behavioral intentions [6]. Customer Segment Prognostic System by Machine Learning using Principal Component and Linear Discriminant Analysis R. Suguna, M. Shyamala Devi, Rincy Merlin Mathew