Data Mining on Supermarket Dataset

Abstract

In the era of science and technology, huge amount of data are recorded every day. According to an article published in MIS Quarterly, a quarterly information system related journal from the University of Minnesota, business intelligence (BI) and business analytics (BA) and the related field of big data analytics have become increasingly important in both the academic and the business communities over the past two decades. Obviously, data analytics is always in the limelight for every business. It can predict customers’ purchasing behavior, calculate for the investment decisions, do risk analysis and management, to name but a few. To be specific, it can help any business to boost sales, improving the services provided, and most importantly, to make smarter and faster decision. Ta Feng grocery dataset will be used in this project. This dataset contains over 8 hundred thousands of transactions from 30 thousands users on 20 thousands items of a Taiwan grocery store. The data were collected from Nov 2000 to Feb 2001. As mentioned before, analytics can help business to find out the status, the problems and opportunities. Therefore the focus of this project will be studying customer purchasing characteristics from the previous transaction records, and provide some marketing strategies for the business to improve the sales.