Direct marketing is to target consumers who are most likely to respond. A number of target selection methods have been employed to select potential customers. These methods either only consider the customer response probability and ignore the profit issue or assume that the estimates of profit are homogenous across customers when considering the expected amount of profit. Furthermore, the traditional analytical techniques based on ordinary least squares (OLS) regression, which focus on the average customer, cannot examine the differences of various customer groups or account for customer heterogeneity in profitability estimates. Quantile regression, instead of the point estimate for the conditional mean, can be used to estimate the whole distribution, especially the upper tail which we are interested in. Quantile regression does not have strict model assumptions as OLS does and is not sensitive to outliers. To model consumer response profit in direct marketing, this thesis tested the endogeneity bias in the recency, frequency, monetary value (RFM) variables using the control function approach, made sample selection bias correction using Heckman’s procedure, and then adopted quantile regression to estimate customer profit and make forecast of the profit distribution of future values. Furthermore, we adopted the recentered influence function (RIF) regression methods proposed by Firpo et al. (2007) to perform unconditional quantile regression for customer profit estimation. The comparison of OLS, conditional and unconditional quantile regression shows that while OLS may induce possible misleading estimation results, conditional and unconditional quantile regression can provide more informative estimation results. The findings can help direct marketers augment the profitability of marketing campaigns and have meaningful implications for solving target marketing forecasting problems given the constraint of limited resources.
|Date of Award||2009|
- Department of Marketing and International Business
|Supervisor||Geng CUI (Supervisor) & Tsang Sing CHAN (Supervisor)|