A structural conflict exists in businesses which sell services whose production costs are discontinuous and whose consumption is continuous but variable. A classic example is in businesses where capital-intensive infrastructure is necessary for provisioning service, but the capacity resulting from capital outlay is not always fully and efficiently utilized. Marketing departments focus on initiatives which increase infrastructure usage to improve both customer retention and on-going revenue. Engineering and operations departments focus on the cost of service provision to improve the capital efficiency of revenue dollar received. Consequently, a marketing initiative to increase infrastructure usage may be resisted by engineering if its introduction would require great capital expense to accommodate that increased usage. This conflict is exacerbated when a usage-enhancing initiative tends to increase usage variability so that capital expenditures are triggered with only small increases in total usage. A data warehouse whose contents encompass both these organizational functions has the potential to mediate this conflict, and data mining can be the tool for this mediation. Marketing databases typically have customer data on rate plans, usage and past response to marketing promotions. Engineering databases generally record infrastructure locations, usages and capacities. Other information is often available from both general domains to allow for the aggregation, or clustering of customer types, rate plans and marketing promotions so that marketing proposals and their consequences can be systematically evaluated to aid in decision making. These databases generally contain such voluminous or complicated data that classical data analysis tools are inadequate. In this chapter, we look at a case study where data mining is applied to predicting capital-intensive resource or infrastructure usage, with the goal of guiding marketing decisions to enable capital efficient marketing. Although the data mining models developed in this chapter do not provide conclusive positions on specific marketing initiatives and their engineering consequences, the usage revenues and infrastructure performance predicted by these models provide systematic, sound, and quantitative input for making balanced and cost-effective business decisions.
In this business context, applying data mining (Berry and Linoff, 2004; Abramowicz and Zurada, 2000; Han and Kamber, 2006; Kantardzic and Zurada, 2005) to capital efficient marketing is illustrated here by a study from wireless telephony (Green, 2000) where marketing plans introduced to utilize excess off-peak network capacity (see Figure 1) could potentially result in requiring fresh capital outlays by indirectly driving peak demand to levels beyond current capacity.
Marketing initiatives to boost average demand can indirectly increase peak demand to beyond capacity.
We specifically consider marketing initiatives—e.g., specific rate plans with free nights and weekends—that are aimed at stimulating off-peak usage. Given a rate plan with a fixed peak minute allowance, availability of extra off-peak minutes could potentially increase peak usage. The quantification of this effect is complicated by the corporate reality of myriad rate plans and geographically extensive and complicated peak usage patterns. In this study, we use data mining methods to analyze customer, call detail, rate plan and cell-site location data to predict the effect of marketing initiatives on busy hour network utilization. This will enable forecasting network cost of service for marketing initiatives thereby leading to optimization of capital outlay.