The Experts below are selected from a list of 58146 Experts worldwide ranked by ideXlab platform
Bart Baesens - One of the best experts on this subject based on the ideXlab platform.
-
a new som based method for profile generation theory and an application in Direct Marketing
European Journal of Operational Research, 2012Co-Authors: Alex Seret, Thomas Verbraken, Sebastien Versailles, Bart BaesensAbstract:The field of Direct Marketing is constantly searching for new data mining techniques in order to analyze the increasing available amount of data. Self-organizing maps (SOM) have been widely applied and discussed in the literature, since they give the possibility to reduce the complexity of a high dimensional attribute space while providing a powerful visual exploration facility. Combined with clustering techniques and the extraction of the so-called salient dimensions, it is possible for a Direct marketer to gain a high level insight about a dataset of prospects. In this paper, a SOM-based profile generator is presented, consisting of a generic method leading to value-adding and business-oriented profiles for targeting individuals with predefined characteristics. Moreover, the proposed method is applied in detail to a concrete case study from the concert industry. The performance of the method is then illustrated and discussed and possible future research tracks are outlined.
-
knowledge discovery in a Direct Marketing case using least squares support vector machines
International Journal of Intelligent Systems, 2001Co-Authors: Stijn Viaene, Bart Baesens, T Van Gestel, Johan A K Suykens, D Van Den Poel, Jan Vanthienen, B De Moor, Guido DedeneAbstract:We study the problem of repeat-purchase modeling in a Direct Marketing setting using Belgian data. More specifically, we investigate the detection and qualification of the most relevant explanatory variables for predicting purchase incidence. The analysis is based on a wrapped form of input selection using a sensitivity based pruning heuristic to guide a greedy, stepwise, and backward traversal of the input space. For this purpose, we make use of a powerful and promising least squares support vector machine (LS-SVM) classifier formulation. This study extends beyond the standard recency frequency monetary (RFM) modeling semantics in two ways: (1) by including alternative operationalizations of the RFM variables, and (2) by adding several other (non-RFM) predictors. Results indicate that elimination of redundant/irrelevant inputs allows significant reduction of model complexity. The empirical findings also highlight the importance of frequency and monetary variables, while the recency variable category seems to be of somewhat lesser importance to the case at hand. Results also point to the added value of including non-RFM variables for improving customer profiling. More specifically, customer/company interaction, measured using indicators of information requests and complaints, and merchandise returns provide additional predictive power to purchase incidence modeling for database Marketing. © 2001 John Wiley & Sons, Inc.
Bongsug Chae - One of the best experts on this subject based on the ideXlab platform.
-
Direct Marketing decision support through predictive customer response modeling
Decision Support Systems, 2012Co-Authors: David L Olson, Bongsug ChaeAbstract:Decision support techniques and models for Marketing decisions are critical to retail success. Among different Marketing domains, customer segmentation or profiling is recognized as an important area in research and industry practice. Various data mining techniques can be useful for efficient customer segmentation and targeted Marketing. One such technique is the RFM method. Recency, frequency, and monetary methods provide a simple means to categorize retail customers. We identify two sets of data involving catalog sales and donor contributions. Variants of RFM-based predictive models are constructed and compared to classical data mining techniques of logistic regression, decision trees, and neural networks. The spectrum of tradeoffs is analyzed. RFM methods are simpler, but less accurate. The effect of balancing cells, of the value function, and classical data mining algorithms (decision tree, logistic regression, neural networks) are also applied to the data. Both balancing expected cell densities and compressing RFM variables into a value function were found to provide models similar in accuracy to the basic RFM model, with slight improvement obtained by increasing the cutoff rate for classification. Classical data mining algorithms were found to yield better prediction, as expected, in terms of both prediction accuracy and cumulative gains. Relative tradeoffs among these data mining algorithms in the context of customer segmentation are presented. Finally we discuss practical implications based on the empirical results.
Man Leung Wong - One of the best experts on this subject based on the ideXlab platform.
-
machine learning for Direct Marketing response models bayesian networks with evolutionary programming
Management Science, 2006Co-Authors: Man Leung WongAbstract:Machine learning methods are powerful tools for data mining with large noisy databases and give researchers the opportunity to gain new insights into consumer behavior and to improve the performance of Marketing operations. To model consumer responses to Direct Marketing, this study proposes Bayesian networks learned by evolutionary programming. Using a large Direct Marketing data set, we tested the endogeneity bias in the recency, frequency, monetary value (RFM) variables using the control function approach; compared the results of Bayesian networks with those of neural networks, classification and regression tree (CART), and latent class regression; and applied a tenfold cross-validation. The results suggest that Bayesian networks have distinct advantages over the other methods in accuracy of prediction, transparency of procedures, interpretability of results, and explanatory insight. Our findings lend strong support to Bayesian networks as a robust tool for modeling consumer response and other Marketing problems and for assisting management decision making.
James D Hess - One of the best experts on this subject based on the ideXlab platform.
-
Direct Marketing inDirect profits a strategic analysis of dual channel supply chain design
Management Science, 2003Co-Authors: Weiyu Kevin Chiang, Dilip Chhajed, James D HessAbstract:The advent of e-commerce has prompted many manufacturers to redesign their traditional channel structures by engaging in Direct sales. The model conceptualizes the impact of customer acceptance of a Direct channel, the degree to which customers accept a Direct channel as a substitute for shopping at a traditional store, on supply-chain design. The customer acceptance of a Direct channel can be strong enough that an indepent manufacturer would open a Direct channel to compete with its own retailers. Here, Direct Marketing is used for strategic channel control purposes even though it is inefficient on its own and, surprisingly, it can profit the manufacturer even when so Direct sales occur. Specifically, we construct a price-setting game between a manufacturer and its independent retailer. Direct Marketing, which inDirectly increases the flow of profits through the retail channel, helps the manufacturer improve overall profitability by reducing the degree of inefficient price double marginalization. While operated by the manufacturer to constrain the retailer's pricing behavior, the Direct channel may not always be detrimental to the retailer because it will be accompanied by a wholesale price reduction. This combination of manufacturer pull and push can benefit the retailer in equilibrium. Finally, we show that the mere threat of introducing the Direct channel can increase the manufacturer's negotiated share of cooperative profits even if price efficiency is obtained by using other business practices.
-
modeling merchandise returns in Direct Marketing
Journal of Direct Marketing, 1997Co-Authors: James D Hess, Glenn E MayhewAbstract:Abstract Returns are a significant problem for many Direct marketers. New models to more accurately explain and predict returns, as well as models that will allow accurate scoring of customers and merchandise for return propensity, would be useful in an industry where returns can exceed 20 percent of sales. We offer a split adjusted hazard model as an alternative to simple regression of return times. We explain why the hazard model is robust and offer an example of its estimation using data of actual returns from an apparel Direct marketer.
-
controlling product returns in Direct Marketing
Marketing Letters, 1996Co-Authors: James D Hess, Wujin Chu, Eitan GerstnerAbstract:Many Direct marketers offer price refunds to unsatisfied consumers, but as a result some consumers order products with no intention of keeping them. We show that such inappropriate returns can be controlled in a profitable way by imposing nonrefundable charges and that these charges increase with the value of the merchandise ordered. Data collected from clothing mail-order catalogs is consistent with our theory. The shipping and handling charges of these catalogs are usually nonrefundable and increase with the value of the merchandise ordered, even when the actual shipping and handling costs are constant.
Guido Dedene - One of the best experts on this subject based on the ideXlab platform.
-
knowledge discovery in a Direct Marketing case using least squares support vector machines
International Journal of Intelligent Systems, 2001Co-Authors: Stijn Viaene, Bart Baesens, T Van Gestel, Johan A K Suykens, D Van Den Poel, Jan Vanthienen, B De Moor, Guido DedeneAbstract:We study the problem of repeat-purchase modeling in a Direct Marketing setting using Belgian data. More specifically, we investigate the detection and qualification of the most relevant explanatory variables for predicting purchase incidence. The analysis is based on a wrapped form of input selection using a sensitivity based pruning heuristic to guide a greedy, stepwise, and backward traversal of the input space. For this purpose, we make use of a powerful and promising least squares support vector machine (LS-SVM) classifier formulation. This study extends beyond the standard recency frequency monetary (RFM) modeling semantics in two ways: (1) by including alternative operationalizations of the RFM variables, and (2) by adding several other (non-RFM) predictors. Results indicate that elimination of redundant/irrelevant inputs allows significant reduction of model complexity. The empirical findings also highlight the importance of frequency and monetary variables, while the recency variable category seems to be of somewhat lesser importance to the case at hand. Results also point to the added value of including non-RFM variables for improving customer profiling. More specifically, customer/company interaction, measured using indicators of information requests and complaints, and merchandise returns provide additional predictive power to purchase incidence modeling for database Marketing. © 2001 John Wiley & Sons, Inc.
