A Novel Propensity-Based Recommendation Approach For Financial Product In Direct Marketing
Abstract
implementation of propensity model only considers the customer’s purchasing probability in a certain marketing campaign, but the
purchasing probability is highly correlated with the product price. In geneal, the higher price the lower response probability, and vice versa.
Therefore, only considering the product’s purchasing probability in a certain marketing campaign cannot maximize the overall potential
revenue. Overselling insurance to cardholders can easily aff ect their experience and cause customer loss. The best way is to off er the right
product to the right customer with the right price in the right time. This article proposes a propensity-based recommendation approach,
which is developed by cardholders’ transaction behavior. Estimation of expected Customer Value on a certain product is done basing on the
purchasing probability. In practice, this approach has been implemented by some retail banks in joint marketing project with life insurance
companies, and achieved quite good results.
Keywords
Full Text:
PDFReferences
[1]Albert Valen ti, Shuba Srinivasan, Gokhan Yildirim, Koen Pauwels. Direct mail to prospects and email to current customers? Modeling and feldtesting
multichannel marketing. Journal of the Academy of Marketing Science (2024) 52:815–834, https://doi.org/10.1007/s11747-023-00962-2
[2]Bart Basens . Credit Risk Analysis[M]. Wiley
[3]Dai, Y., & Wang, T. (2021). Prediction of customer engagement behaviour response to marketing posts based on machine learning. Connection
Science, 33(4), 891–910. https://doi.org/10.1080/09540091.2021.1912710
[4]David W.Hosmer, Stanley Lemesbow. Applied Logistic Regression, 2nd Edition[M]. Wiley
[5]Deng Lihua, Zhang Liangping. Life insurance recommendation model based on data mining technology[J], Value Engineering, 2015.21.012
[6]Gu Shengjia, Xu Qinyan, Yang Yang, Wang Wei. Use neural network technology to achieve life insurance product recommendation[J], Experience Exchange. 2017.10.180
[7]Greig Cowan, Salvatore Mercuri, Raad Khraishi. Modelling customer lifetime-value in the retail banking industry[J]. arXiv:2304.03038v1 [cs.LG] 6 Apr
2023
[8]Hyunseung Kang, Chan Park, and Ralph Trane. Propensity Score Modeling: Key Challenges When Moving Beyond the No-Interference Assumption[J].
arXiv:2208.06533v1 [stat.ME] 13 Aug 202
[9]Jing LI, Shuxiao PAN, Lei HUANG, Xin ZHU. A Machine Learning Based Method for Customer Behavior Prediction[J]. Technical Gazette 26, 6(2019),
1670-1676. https://doi.org/10.17559/TV-20190603165825
[10]Linden G, Smith B, York J.Amazon.com recommendations: Item-to-item collaborative fi ltering[J]. IEEE Internet computing, 2003, 7(1): 76-80.
[11]Roman Kubiak. Net Lift Model for Eff ective Direct Marketing Campaigns at 1800fl owers.com.[J] In SAS Global Forum 2012, Paper108-2012
[12]Xiang Liang. Recommended system for actual combat [M]. Beijing: People’s Posts and Telecommunications Press, 2012.
[13]Yin Ming, the application and prospect of new technologies such as artifi cial intelligence in the insurance industry, Tsinghua Financial Financial Review,
2017.12.013
[14]Ye Bi, Liqiang Song, Mengqiu Yao, Zhenyu Wu, Jianming Wang, Jing Xiao. A Heterogeneous Information Network based Cross Domain Insurance
Recommendation System for Cold Start Users[J]. arXiv:2007.15293v1 [cs.IR] 30 Jul 2020
[15]Henrika Langen and Martin Huber. How causal machine learning can leverage marketing strategies: Assessing and improving the performance of a
coupon campaign[J]. arXiv:2204.10820v2 [econ.GN] 22 Jun 2022
[16]Sentheni Manimaran, Khai Yin Lim. Customer Propensity Model: Marketing Campaign[J]. On 2024 3rd International Conference on Digital
Transformation and Applications (ICDXA) | 979-8-3503-7342-4/24/$31.00 ©2024 IEEE
[17]Sunˇcica Rogi´c, Ljiljana Kaš´celan, Mirjana Peji´c Bach. Customer Response Model in Direct Marketing: Solving the Problem of Unbalanced Dataset
with a Balanced Support Vector Machine[J]. Theoretical and Applied Electronic Commerce Research, 2022, 17, 1003-1008, https://www.mdpi.com/0718-
1876/17/3/51
[18]Yue Zhang. Prediction of Customer Propensity Based on Machine Learning[J]. On 2021 Asia-Pacifi c Conference on Communications Technology and
Computer Science (ACCTCS) | 978-1-6654-1538-5/21/$31.00
DOI: http://dx.doi.org/10.18686/modern-management-forum.v8i7.13653
Refbacks
- There are currently no refbacks.
