Mining Retail Telecommunication Data to Predict Profitability

Small or early-stage businesses often require sources of equity, loans, and/or debt funding to support their growth. An important part of the documentation accompanying funding requests can be derived from analytical data associated with the business. There are numerous commercial business intelligence (BI) tools to monitor data and generate business insights. However, most of the retail entrepreneurs still use manual and/or simple techniques, having little time to dedicate to sophisticated BI tools. In this work, we consider how supervised learning models can be used for retail telecommunications businesses. Specifically, we examine how nearest neighbour techniques, feed forward artificial neural networks, Bayesian classifiers, and support vector machines can be used with retail telecommunication data. As indicated by our initial results we have been able to achieve precision of 95.5%, recall of 94.7%, and f-measure of 95.1% which demonstrates that we can categorize retail telecommunication data based on the profitability.