Integrating Ensembling Schemes with Classification for Customer Group Prediction using Machine Learning
R. Suguna1, M. Shyamala Devi2, Rincy Merlin Mathew3
1R. Suguna, Professor, Computer Science and Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, Chennai, TamilNadu, India.
2M. Shyamala Devi, Associate Professor, Computer Science and Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, Chennai, TamilNadu, India.
3Rincy Merlin Mathew, Lecturer, Department of Computer Science, College of Science and Arts, Khamis Mushayt, King Khalid university, Abha, Asir, Saudi Arabia.
Manuscript received on July 20, 2019. | Revised Manuscript received on August 10, 2019. | Manuscript published on August 30, 2019. | PP: 957-961 | Volume-8 Issue-6, August 2019. | Retrieval Number: F8256088619/2019©BEIESP | DOI: 10.35940/ijeat.F8256.088619
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In current marketing scenario, it is highly difficult to earn the high profit by satisfying the customers as well to increase to turn over of the company. For increasing the profit, the organizations are struggling to find a method to analyze their marketing strategy and to understand the customer’s requirements. The main solution to increase the profit of any organization is to manufacture the limited and the needed goods based on the customer’s needs and dislikes. For this, they need to find the customers behavior and the opinion regarding their products. This claims the usage of machine learning algorithms to predict and analyze the behavior of the customer. With this information scenario, we have extracted the wine data set from UCI Machine learning repository. The wine data set is analyzed to decide the dependent and independent variable. The dimensionality reduction is done by applying the ensembling methods. The feature importance of the various ensembling methods like Ada boost regressor, Ada boost classifier, Random forest regressor, Extra Trees Regressor and Gradient booster regressor. The extracted feature importance of the wine data set is fitted with logistic regression classifier to analyse the performance of the each ensembling methods. The metrics used for performance analysis are accuracy, precision, recall, and f-score. Experimental results shows that feature importance obtained from Ada Boost regressor fitted with logistic regression classifier is found to be effective with the accuracy of 94%, Precision of 0.95, Recall of 0.94 and FScore of 0.94 compared to other ensembling methods.
Keywords: Machine Learning, Classification, accuracy, precision, recall, and f-score.