The true lift model: a novel data mining approach to response modeling in database marketing

ABSTRACT

In database marketing, data mining has been used extensively to find the optimal customer targets so as to maximize return on investment. In particular, using marketing campaign data, models are typically developed to identify characteristics of customers who are most likely to respond. While these models are helpful in identifying the likely responders, they may be targeting customers who have decided to take the desirable action or not regardless of whether they receive the campaign contact (e.g. mail, call). Based on many years of business experience, we identify the appropriate business objective and its associated mathematical objective function. We point out that the current approach is not directly designed to solve the appropriate business objective. We then propose a new methodology to identify the customers whose decisions will be positively influenced by campaigns. The proposed methodology is easy to implement and can be used in conjunction with most commonly used supervised learning algorithms. An example using simulated data is used to illustrate the proposed methodology. This paper may provide the database marketing industry with a simple but significant methodological improvement and open a new area for further research and development.

REFERENCES

• 1: Almquist, E. and Wyner G. Boost your marketing ROI with experimental design. Harvard Business Review, Oct, 2001, p. 135--141.
• 2: Michael J. Berry , Gordon Linoff, Data Mining Techniques: For Marketing, Sales, and Customer Support, John Wiley & Sons, Inc., New York, NY, 1997
• 3: Berry, M.J.A. and Linoff, G.S. Mastering Data Mining. Wiley, 2000.
• 4: Blattberg, R.C., Getz, G., and Thomas J.S. Customer Equity: Building and Managing Relationships As Valuable Assets. Harvard Business School Press, 2001.
• 5: N. K. Bose , P. Liang, Neural network fundamentals with graphs, algorithms, and applications, McGraw-Hill, Inc., Hightstown, NJ, 1996
• 6: Breiman, L., Olson, R., Friedman, J., and Stone, C. Classification and Regression Trees. Chapman & Hall, 1984.
• 7: Collett, D. Modeling Survival Data in Medical Research. Chapman & Hall, 1997, p. 241--249.
• 8: Edward J. Dudewicz , Satya Mishra, Modern mathematical statistics, John Wiley & Sons, Inc., New York, NY, 1988
• 9: Fabris, P. Advanced navigation: Marketing secrets from the financial sector show how data mining charts a profitable course to customer management. CIO magazine, 11, No.15, 1998, p. 50--55.
• 10: Goetghebeur, E. and Lapp, K. The effect of treatment compliance in a placebo-controlled trial: regression with unpaired data. Applied Statistics, 46, No.3, 1997, p. 351--364.
• 11: Guo, H. and Gelfand, S.B. Classification trees with neural network feature extraction. IEEE Transactions on Neural Networks, 3, No.6, 1992, p. 923--933.
• 12: Simon Haykin, Neural Networks: A Comprehensive Foundation, Prentice Hall PTR, Upper Saddle River, NJ, 1998
• 13: David Heckerman, Bayesian Networks for Data Mining, Data Mining and Knowledge Discovery, v.1 n.1, p.79-119, 1997 [doi>10.1023/A:1009730122752]
• 14: Henery, R.J. Combining classification procedures. In Machine Learning and Statistics, The Interface, by Nakhaeizadeh, G. and Taylor, C.C. (ed.). Wiley, 1997, p. 153--177.
• 15: Holmgren, E.B. and Koch, G.G. Statistical modeling of dose-response relationships in clinical trials -- a case study. Journal of Biopharmaceutical Statistics, 7, No.2, 1997, p. 301--312.
• 16: Hosmer, D.W. and Lemeshow, S. Applied Logistic Regression. Wiley, 1989.
• 17: Hughes, A.M. Strategic Database Marketing. McGrawHill, 1994.
• 18: W. H. Inmon , Richard D. Hackathorn, Using the data warehouse, Wiley-QED Publishing, Somerset, NJ, 1994
• 19: Jackson, R. and Wang, P. Strategic Database Marketing. NTC Publishing, 1996.
• 20: Finn V. Jensen , F.V. V. Jensen , F. V. Jensen, Introduction to Bayesian Networks, Springer-Verlag New York, Inc., Secaucus, NJ, 1996
• 21: Koch, T.W. Bank Management, 3rd edition. Dryden, 1995, p. 352.
• 22: Kotler, P. Marketing Management, 8th edition. Prentice-Hall, 1994, chapter 24.
• 23: Leonard, J.A., Kramer, M.A., and Ungar, L.H. Using radial basis functions to approximate a function and its error bounds. IEEE Transactions on Neural Networks, 3, No.4, 1992, p. 624--627.
• 24: Boaz Lerner , Hugo Guterman , Mayer Aladjem , Its'hak Dinstein, A comparative study of neural network based feature extraction paradigms, Pattern Recognition Letters, v.20 n.1, p.7-14, Jan. 1999 [doi>10.1016/S0167-8655(98)00120-2]
• 25: McKinney, R.E., Johnson, G.M., Stanley, K., Yong, F., Keller, A., O'Donnel, K.J., Brouwers, P., Mitchell, W.G., Yogev, R., Wara, D.W., Wiznia, A., Mofenson, L., McNamara, J., Spector, S.A., and the Pediatric AIDS Clinical Trials Group Protocol 300 Study Team. A randomized study of combined zidovudine-lamivudine versus didanosine monotherapy in children with sympotomatic therapy-naïve HIV-1 infection. Journal of Pediatrics, 133, No.4, 1998, p. 500--508.
• 26: Mojirsheibani, M. Combining classifers via discretization. Journal of the American Statistical Association, 94, No.446, 1999, p. 600--609.
• 27: Montgomery, D.C. Design and Analysis of Experiments, 3rd edition. Wiley, 1991, p. 79--80.
• 28: Sreerama K. Murthy, Automatic Construction of Decision Trees from Data: A Multi-Disciplinary Survey, Data Mining and Knowledge Discovery, v.2 n.4, p.345-389, December 1998 [doi>10.1023/A:1009744630224]
• 29: Peppers, D. and Rogers, M. Enterprise One-to-One. Doubleday, 1999.
• 30: Peppers, D. and Rogers, M. The One-to-One Fieldbook. Doubleday, 1999.
• 31: Gregory Piatetsky-Shapiro , Sam Steingold, Measuring lift quality in database marketing, ACM SIGKDD Explorations Newsletter, v.2 n.2, p.76-80, Dec. 2000 [doi>10.1145/380995.381018]
• 32: Roberts, M.L. and Berger P.D. Direct Marketing Management. Prentice-Hall, 1999.
• 33: Rud, O.P. Data Mining Cookbook. Wiley, 2001.
• 34: Russek-Cohen, E. and Simon, R.M. Evaluating treatments when a gender by treatment interaction may exist. Statistics in Medicine, 16, issue 4, 1997, p. 455--464.
• 35: Specht, D.F. A general regression neural network. IEEE Transactions on Neural Network, 2, No.6, 1991, p. 568--576.
• 36: Wahba, G. Spline Models for Observational Data. Society for Industrial and Applied Mathematics, 1992.
• 37: Wang, P. and Puterman, M.L. Mixed logistic regression models. Journal of Agricultural, Biological, and Environmental Statistics, 3, No.2, 1998, p. 175--200.
• 38: Zhang, H. and Singer, B. Recursive Partitioning in the Health Sciences. Springer, 1999.

INDEX TERMS

Keywords:
customer development, customer relationship management, data mining, database marketing, interaction effect, knowledge discovery, predictive modeling, response modeling, treatment effect, true lift, upselling and cross-selling