IRMA-International.org: Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

Efficient End-to-End Asynchronous Time-Series Modeling With Deep Learning to Predict Customer Attrition

Efficient End-to-End Asynchronous Time-Series Modeling With Deep Learning to Predict Customer Attrition
View Sample PDF
Author(s): Victor Potapenko (Florida International University, USA), Malek Adjouadi (Florida International University, USA)and Naphtali Rishe (Florida International University, USA)
Copyright: 2021
Pages: 14
Source title: Handbook of Research on Methodologies and Applications of Supercomputing
Source Author(s)/Editor(s): Veljko Milutinović (Indiana University, Bloomington, USA)and Miloš Kotlar (University of Belgrade, Serbia)
DOI: 10.4018/978-1-7998-7156-9.ch016

Purchase

View Efficient End-to-End Asynchronous Time-Series Modeling With Deep Learning to Predict Customer Attrition on the publisher's website for pricing and purchasing information.

Abstract

Modeling time-series data with asynchronous, multi-cardinal, and uneven patterns presents several unique challenges that may impede convergence of supervised machine learning algorithms, or significantly increase resource requirements, thus rendering modeling efforts infeasible in resource-constrained environments. The authors propose two approaches to multi-class classification of asynchronous time-series data. In the first approach, they create a baseline by reducing the time-series data using a statistical approach and training a model based on gradient boosted trees. In the second approach, they implement a fully convolutional network (FCN) and train it on asynchronous data without any special feature engineering. Evaluation of results shows that FCN performs as well as the gradient boosting based on mean F1-score without computationally complex time-series feature engineering. This work has been applied in the prediction of customer attrition at a large retail automotive finance company.

Related Content

Miloš Kotlar. © 2021. 4 pages.
Ivan Ratković, Miljan Djordjevic. © 2021. 13 pages.
Benjamin Berg, Mor Harchol-Balter. © 2021. 23 pages.
Bryan Donyanavard, Amir M. Rahmani, Axel Jantsch, Onur Mutlu, Nikil Dutt. © 2021. 33 pages.
Assefaw Gebremedhin, Mostofa Patwary, Fredrik Manne. © 2021. 22 pages.
Nenad Korolija, Jovan Popović, Miroslav M. Bojović. © 2021. 10 pages.
Christina Pacher. © 2021. 8 pages.
Body Bottom