International Journal of Engineering and Advanced Technology (IJEAT) ISSN: 2249 – 8958, Volume-8 Issue-6, August 2019 952 Published By: Blue Eyes Intelligence Engineering & Sciences Publication Retrieval Number F8255088619/2019©BEIESP DOI: 10.35940/ijeat.F8255.088619 Abstract: Prediction of client behavior and their feedback remains as a challenging task in today’s world for all the manufacturing companies. The companies are struggling to increase their profit and annual turnover due to the lack of exact prediction of customer like and dislike. This leads to the accomplishment of machine learning algorithms for the prediction of customer demands. This paper attempts to identify the important features of the wine data set extracted from UCI Machine learning repository for the prediction of customer segment. The important features are extracted for the various ensembling methods like Ada boost regressor, Ada boost classifier, Random forest regressor, Extra Trees Regressor, Gradient booster regressor. The extracted feature importance of each of the ensembling methods is then fitted with logistic regression to analyze the performance. The same extracted feature importance of each of the ensembling methods are subjected to feature scaling and then fitted with logistic regression to analyze the performance. The Performance analysis is done with the performance metric such as Mean Squared error (MSE), Mean Absolute error (MAE), R2 Score, Explained Variance Score (EVS) and Mean Squared Log Error (MSLE). Experimental results shows that after applying feature scaling, the feature importance extracted from the Extra Tree Regressor is found to be effective with the MSE of 0.04, MAE of 0.03, R2 Score of 94%, EVS of 0.9 and MSLE of 0.01 as compared to other ensembling methods. Index Terms: Machine Learning, Mean Squared error, Mean Absolute error, R2 Score, Explained Variance Score and Mean Squared Log Error. I. INTRODUCTION Generally the dataset in the market have a lot of attributes. The single dependent variable of the dataset is predicted by the occurrence of one or more independent variables. However, the dependent variable does not need the existence of all independent variable for its predicted. Some of the independent variable are not at all involved in the prediction of the target variable. So it is very essential to find the Revised Manuscript Received on August 05, 2019 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. R. Suguna, Professor, Computer Science and Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, Chennai, TamilNadu, India. important features of the machine learning dataset so as to predict the value of the dependent variable with high accuracy. 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 The chemical samples and its proposition is needed to predict the quality of wine. Due to the change in the mixing of the chemicals and their existence in the wine, the quality of wine greatly changes. Based on the quality of the wine, the customers prefer the product. The machine learning models can be built to find the exact combination of the chemicals to be added based on the customers behavior. The machine learning models like Linear Regression, Decision Trees and Artificial Neural Networks are used to predict the customer behavior that helps in finding the needed features to understand the customer’s behavior and demand [1]. The data mining techniques are used to predict the customers need and their behavior in choosing the wine. The statistics that are involved in the data mining techniques can find the exact combination of the independent variables that are present in the dataset [2]. The customer relationship management is greatly needed for any business to survive in the current market world. The utilization charge of wine was evaluated using various factors like such as manufactured goods involvement, biased awareness, delicate qualities and socio demography [3]. Due to the growth in the online shopping, the customers wish to buy the high quality wine through online web portal shopping. In this scenario, the customers just view the quality of the wine only through the ingredients present in the wine [4]. The various wine brands has worth in their improvement and the current market is highly competitive [5]. A critical review on various feature selection, feature extraction methods, classification methods and the performances parameters are examined for predicting the wine quality [6]-[10]. Regressor Fitting Of Feature Importance For Customer Segment Prediction With Ensembling Schemes Using Machine Learning M. Shyamala Devi, Rincy Merlin Mathew, R. Suguna