Customer Life Time Value Model Framework Using Gradient Boost Trees with RANSAC Response Regularization

Lavneet SINGH, Nancy Kaur, Girija CHETTY

Research output: A Conference proceeding or a Chapter in BookConference contribution

Abstract

For many years, Customer lifetime value has been a mainstay concept in direct response marketing and has been increasingly considered. This paper presents a mathematical model framework for determination of customer lifetime value. The proposed multi-layer framework is based on a systematic theoretical taxonomy and on assumptions grounded in customer behavior. CLV, a recent marketing paradigm, pursues long-term relationship with profitable customers. It can be a starting point to understand relationship management and measure the true value of customers to be deployed toward the targeted customers and profitable customers, to foster customers’ full profit potential. Corporate success depends on an organization ’ ability to build and maintain loyal and valued customer relationships. In this paper, we propose a framework for analyzing customer value and segmenting customers based on their value. We also conducted an in-depth data analysis to find each member’s behavior and important attributes which plays a significant role in calculating CLV in multiple revenue bands. From the experimental validation, we concluded that our proposed framework works much better in predicting customer’s life time value in terms of revenue compared to other methods in past literature.
Original languageEnglish
Title of host publicationProceedings 2018 International Joint Conference on Neural Networks (IJCNN)
Place of PublicationRio de Janeiro, Brazil, Brazil
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1527-1534
Number of pages8
ISBN (Electronic)9781509060146
ISBN (Print)9781509060153
DOIs
Publication statusPublished - 8 Jul 2018
EventIEEE International Conference on Neural Networks -
Duration: 1 Jan 2011 → …

Conference

ConferenceIEEE International Conference on Neural Networks
Abbreviated titleICNN
Period1/01/11 → …

Fingerprint

Marketing
Taxonomies
Profitability
Mathematical models

Cite this

SINGH, L., Kaur, N., & CHETTY, G. (2018). Customer Life Time Value Model Framework Using Gradient Boost Trees with RANSAC Response Regularization. In Proceedings 2018 International Joint Conference on Neural Networks (IJCNN) (pp. 1527-1534). Rio de Janeiro, Brazil, Brazil: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IJCNN.2018.8489710
SINGH, Lavneet ; Kaur, Nancy ; CHETTY, Girija. / Customer Life Time Value Model Framework Using Gradient Boost Trees with RANSAC Response Regularization. Proceedings 2018 International Joint Conference on Neural Networks (IJCNN). Rio de Janeiro, Brazil, Brazil : IEEE, Institute of Electrical and Electronics Engineers, 2018. pp. 1527-1534
@inproceedings{a4dc533e89a04b18b55bab4edc20fbb4,
title = "Customer Life Time Value Model Framework Using Gradient Boost Trees with RANSAC Response Regularization",
abstract = "For many years, Customer lifetime value has been a mainstay concept in direct response marketing and has been increasingly considered. This paper presents a mathematical model framework for determination of customer lifetime value. The proposed multi-layer framework is based on a systematic theoretical taxonomy and on assumptions grounded in customer behavior. CLV, a recent marketing paradigm, pursues long-term relationship with profitable customers. It can be a starting point to understand relationship management and measure the true value of customers to be deployed toward the targeted customers and profitable customers, to foster customers’ full profit potential. Corporate success depends on an organization ’ ability to build and maintain loyal and valued customer relationships. In this paper, we propose a framework for analyzing customer value and segmenting customers based on their value. We also conducted an in-depth data analysis to find each member’s behavior and important attributes which plays a significant role in calculating CLV in multiple revenue bands. From the experimental validation, we concluded that our proposed framework works much better in predicting customer’s life time value in terms of revenue compared to other methods in past literature.",
keywords = "Boosting, Neural networks, Regularization",
author = "Lavneet SINGH and Nancy Kaur and Girija CHETTY",
year = "2018",
month = "7",
day = "8",
doi = "10.1109/IJCNN.2018.8489710",
language = "English",
isbn = "9781509060153",
pages = "1527--1534",
booktitle = "Proceedings 2018 International Joint Conference on Neural Networks (IJCNN)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

SINGH, L, Kaur, N & CHETTY, G 2018, Customer Life Time Value Model Framework Using Gradient Boost Trees with RANSAC Response Regularization. in Proceedings 2018 International Joint Conference on Neural Networks (IJCNN). IEEE, Institute of Electrical and Electronics Engineers, Rio de Janeiro, Brazil, Brazil, pp. 1527-1534, IEEE International Conference on Neural Networks, 1/01/11. https://doi.org/10.1109/IJCNN.2018.8489710

Customer Life Time Value Model Framework Using Gradient Boost Trees with RANSAC Response Regularization. / SINGH, Lavneet; Kaur, Nancy; CHETTY, Girija.

Proceedings 2018 International Joint Conference on Neural Networks (IJCNN). Rio de Janeiro, Brazil, Brazil : IEEE, Institute of Electrical and Electronics Engineers, 2018. p. 1527-1534.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Customer Life Time Value Model Framework Using Gradient Boost Trees with RANSAC Response Regularization

AU - SINGH, Lavneet

AU - Kaur, Nancy

AU - CHETTY, Girija

PY - 2018/7/8

Y1 - 2018/7/8

N2 - For many years, Customer lifetime value has been a mainstay concept in direct response marketing and has been increasingly considered. This paper presents a mathematical model framework for determination of customer lifetime value. The proposed multi-layer framework is based on a systematic theoretical taxonomy and on assumptions grounded in customer behavior. CLV, a recent marketing paradigm, pursues long-term relationship with profitable customers. It can be a starting point to understand relationship management and measure the true value of customers to be deployed toward the targeted customers and profitable customers, to foster customers’ full profit potential. Corporate success depends on an organization ’ ability to build and maintain loyal and valued customer relationships. In this paper, we propose a framework for analyzing customer value and segmenting customers based on their value. We also conducted an in-depth data analysis to find each member’s behavior and important attributes which plays a significant role in calculating CLV in multiple revenue bands. From the experimental validation, we concluded that our proposed framework works much better in predicting customer’s life time value in terms of revenue compared to other methods in past literature.

AB - For many years, Customer lifetime value has been a mainstay concept in direct response marketing and has been increasingly considered. This paper presents a mathematical model framework for determination of customer lifetime value. The proposed multi-layer framework is based on a systematic theoretical taxonomy and on assumptions grounded in customer behavior. CLV, a recent marketing paradigm, pursues long-term relationship with profitable customers. It can be a starting point to understand relationship management and measure the true value of customers to be deployed toward the targeted customers and profitable customers, to foster customers’ full profit potential. Corporate success depends on an organization ’ ability to build and maintain loyal and valued customer relationships. In this paper, we propose a framework for analyzing customer value and segmenting customers based on their value. We also conducted an in-depth data analysis to find each member’s behavior and important attributes which plays a significant role in calculating CLV in multiple revenue bands. From the experimental validation, we concluded that our proposed framework works much better in predicting customer’s life time value in terms of revenue compared to other methods in past literature.

KW - Boosting

KW - Neural networks

KW - Regularization

UR - https://ieeexplore.ieee.org/document/8489710

U2 - 10.1109/IJCNN.2018.8489710

DO - 10.1109/IJCNN.2018.8489710

M3 - Conference contribution

SN - 9781509060153

SP - 1527

EP - 1534

BT - Proceedings 2018 International Joint Conference on Neural Networks (IJCNN)

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Rio de Janeiro, Brazil, Brazil

ER -

SINGH L, Kaur N, CHETTY G. Customer Life Time Value Model Framework Using Gradient Boost Trees with RANSAC Response Regularization. In Proceedings 2018 International Joint Conference on Neural Networks (IJCNN). Rio de Janeiro, Brazil, Brazil: IEEE, Institute of Electrical and Electronics Engineers. 2018. p. 1527-1534 https://doi.org/10.1109/IJCNN.2018.8489710