Analysis of customer data using hybridized machine learning technique along with data exploration methods

  • Authors

    • G. S. Ramesh VNR VJIET
    • Dr. T V Rajini Kanth SNIST
    • Dr. D Vasumaathi JNTUH
    https://doi.org/10.14419/ijet.v7i4.15246

    Received date: July 8, 2018

    Accepted date: September 16, 2018

    Published date: November 15, 2018

  • Business Intelligence, Data Exploration, Logistic Model Tree, Machine Learning, Visual Analytics.

  • Abstract

    The introduction of Information Communication Technologies (ICT) like POS and sensors into retail and marketing the Sales Data and Customer data are increasing day by day seamlessly without any limitation and boundaries in an exponential growth. This huge voluminous data is threatening research community to develop suitable models for the identifying Target Customers, enhancement of particular Products sales etc. The need of Business Intelligence techniques is very much required in this scenario to address the Entrepreneurs, Business community. The Machine learning algorithms are also useful to Analyze Sales Volume or to Discover Most Likely to Buy Products or to Provide Price Recommendations. This paper addresses these problems with the help of data exploration using Visual Analytics techniques apart from predictive analytics. The Machine learning algorithms like K-mean Clustering, Logistic Model tree together as a hybridized Clustered based Logistic Model tree algorithm was applied apart from machine learning Data exploration techniques. Visual Comparisons were also made along with advanced statistical techniques and summarized the results for better conclusions.

  • References

    1. Rudradeb Mitra, “Predicting buying behavior using Machine Learn-ing: A case study on Sales Prospecting (Part I)”, https://becominghuman.ai/predicting-buying-behavior-using-machine-learning-a-case-study-on-sales-prospecting-part-i-3bf455486e5d.
    2. Chris Glass, “7 Ways Machine Learning Boosts Sales Performance and Drives Revenue Growth”, https://optymyze.com/blog/7-ways-machine-learning-boosts-sales-performance-and-drives-revenue-growth/.
    3. Rajan Gupta, Chaitanya Pathak, “A Machine Learning Framework for Predicting Purchase by Online Customers based on Dynamic Pricing”, Elsevier Procedia Computer Science 36(2014) 599 – 605, www.sciencedirect.com.
    4. Yuta Kaneko, Katsutoshi Yada, “A Deep Learning Approach for the Prediction of Retail Store Sales”, IEEE 16th International Confer-ence on Data Mining Workshops (ICDMW), 2016, Electronic ISBN: 978-1-5090-5910-2, Electronic ISSN: 2375-9259, DOI: 10.1109/ICDMW. 2016.0082.
    5. Yi Zuo, Katsutoshi Yada, A.B.M. Shawkat Ali, “Prediction of Con-sumer Purchasing in a Grocery Store Using Machine Learning Techniques”, 3rd Asia-Pacific World Congress on Computer Sci-ence and Engineering (APWC on CSE), 2016, Electronic ISBN: 978-1-5090-5753-5, https://doi.org/10.1109/APWC-on-CSE.2016.015.
    6. Stefan Meinzer, Ulf Jensen, Alexander Thamm, Joachim Hornegger, Björn M. Eskofier, “Can machine learning techniques predict cus-tomer dissatisfaction? A feasibility study for the automotive indus-try”, 2017, Vol. 6, No. 1, Artificial Intelligence Research, URL: https://doi.org/10.5430/air.v6n1p80.
    7. S.HanumanthSastry and Prof.M.S.PrasadaBabu, “Analysis & Pre-diction Of Sales Data In Saperp System Using Clustering Algo-rithms”, International Journal of Computational Science and Infor-mation Technology (IJCSITY) Vol.1, No.4, November 2013. https://doi.org/10.5121/ijcsity.
    8. Vaughn Aust, Machine Learning Can Turn Your Sales Team into Closers By drawing correlations out of massive amounts of customer data, machine learning can better inform the sales process—and ena-ble your reps to close more deals, https://destinationCRM.com.
    9. Cristina STOICESCU, “Big Data, the perfect instrument to study today’s consumer behavior”, Big Data, the perfect instrument to study today’s consumer behavior. Database Systems Journal vol. VI, no. 3/2015.
    10. Daniel Faggella, “Predictive Analytics for Marketing – What’s Pos-sible and How it Works”, https://www.techemergence.com/predictive-analytics-for-marketing-whats-possible-and-how-it-works/.
    11. Bernard Marr, How Machine Learning Will Transform the Sales Function, https://www.forbes.com/sites/bernardmarr/2017/07/06/how-machine-learning-will-transform-the-sales-function/#3672c05f23d7.
    12. Reid Pryzant, Young-joo Chung, Dan Jurafsky, Predicting Sales from the Language of Product Descriptions, Proceedings of SIGIR, Tokyo, Japan, August 2017 (SIGIR 2017 eCom), 10 pages.
    13. Kris Johnson Ferreira, Bin Hong Alex Lee, David Simchi-Lev, Ana-lytics for an Online Retailer: Demand Forecasting and Price Optimi-zation, https://www.hbs.edu/faculty/Publication%20Files/kris%20Analytics%20for%20an%20Online%20Retailer_6ef5f3e6-48e7-4923-a2d4-607d3a3d943c.pdf.
    14. Robert Siwerz, Christopher Dahlén, Predicting sales in a food store department using machine learning, Degree Project In Computer En-gineering, First Cycle, 15 Credits Stockholm, Sweden 2017.
    15. Abreu, N. (2011). Analise do perfil do cliente Recheio e desenvol-vimento de um sistema promocional. Mestrado em Marketing, IS-CTE-IUL, Lisbon.
    16. Niels Landwehr, Mark Hall, Eibe Frank (2005). Logistic Model Trees. Machine Learning. 95(1-2):161-205. https://doi.org/10.1007/s10994-005-0466-3.
    17. Marc Sumner, Eibe Frank, Mark Hall: Speeding up Logistic Model Tree Induction. In: 9th European Conference on Principles and Prac-tice of Knowledge Discovery in Databases, 675-683, 2005. https://doi.org/10.1007/11564126_72.

  • Downloads

  • How to Cite

    S. Ramesh, G., T V Rajini Kanth, D., & D Vasumaathi, D. (2018). Analysis of customer data using hybridized machine learning technique along with data exploration methods. International Journal of Engineering and Technology, 7(4), 4388-4392. https://doi.org/10.14419/ijet.v7i4.15246