Exportar Publicação

Moro, S., Cortez, Paulo & Rita, P. (2015). Using customer lifetime value and neural networks to improve the prediction of bank deposit subscription in telemarketing campaigns. Neural Computing and Applications. 26 (1), 131-139

S. M. Moro et al.,  "Using customer lifetime value and neural networks to improve the prediction of bank deposit subscription in telemarketing campaigns", in Neural Computing and Applications, vol. 26, no. 1, pp. 131-139, 2015

@article{moro2015_1714870525762,
	author = "Moro, S. and Cortez, Paulo and Rita, P.",
	title = "Using customer lifetime value and neural networks to improve the prediction of bank deposit subscription in telemarketing campaigns",
	journal = "Neural Computing and Applications",
	year = "2015",
	volume = "26",
	number = "1",
	doi = "10.1007/s00521-014-1703-0",
	pages = "131-139",
	url = "http://link.springer.com/article/10.1007/s00521-014-1703-0"
}

TY  - JOUR
TI  - Using customer lifetime value and neural networks to improve the prediction of bank deposit subscription in telemarketing campaigns
T2  - Neural Computing and Applications
VL  - 26
IS  - 1
AU  - Moro, S.
AU  - Cortez, Paulo
AU  - Rita, P.
PY  - 2015
SP  - 131-139
SN  - 0941-0643
DO  - 10.1007/s00521-014-1703-0
UR  - http://link.springer.com/article/10.1007/s00521-014-1703-0
AB  - Customer lifetime value (LTV) enables using client characteristics, such as recency, frequency and monetary value, to describe the value of a client through time in terms of profitability. We present the concept of LTV applied to telemarketing for improving the return-on-investment, using a recent (from 2008 to 2013) and real case study of bank campaigns to sell long-term deposits. The goal was to benefit from past contacts history to extract additional knowledge. A total of twelve LTV input variables were tested, under a forward selection method and using a realistic rolling windows scheme, highlighting the validity of five new LTV features. The results achieved by our LTV data-driven approach using neural networks allowed an improvement up to 4 pp in the Lift cumulative curve for targeting the deposit subscribers when compared with a baseline model (with no history data). Explanatory knowledge was also extracted from the proposed model, revealing two highly relevant LTV features, the last result of the previous campaign to sell the same product and the frequency of past client successes. The obtained results are particularly valuable for contact center companies, which can improve predictive performance without even having to ask for more information to the companies they serve.
ER  -