search for




 

Travel index forecasting using credit card transaction
Journal of the Korean Data & Information Science Society 2021;32:199-212
Published online January 31, 2021;  https://doi.org/10.7465/jkdi.2021.32.1.199
© 2021 Korean Data and Information Science Society.

Hyeri Yi1 · Suk Woo Kang2 · Min-Hee Kim3

123Hana Institute of Technology
Correspondence to: 1Senior data scientist, Hana Institute of Technology, 127 Teheran-ro Seoul 06133, Korea.
2Associate data scientist, Hana Institute of Technology, 127 Teheran-ro Seoul 06133, Korea.
3Corresponding author : Lead data scientist, Ph.D in Statistics, Hana Institute of Technology, 127 Teheran-ro Seoul 06133, Korea. E-mail: mh0325.kim@hanafn.com
Received November 15, 2020; Revised December 31, 2020; Accepted January 3, 2021.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
Credit card data is one of the most important data that reflects the lives of customers. Effective marketing requires understanding the customer’s life, so in this paper we build a predictive model that predicts the customer’s life through credit card transaction data. In particular, focus on how to predict customers who are likely to leave ’overseas travel’ during various life events. There are many existing predictive model methodologies, but this study presents the FastText methodology, which is applied primarily to text data, and the newly proposed adaptive sum of term scoring (AWST score).
Keywords : Credit card transaction, CRM, FastText, life event prediction model, marketing Modeling, TF-IDF.