An Enhanced Deep Learning Approach to Potential Purchaser Prediction: AutoGluon Ensembles for Cross-Industry Profit Maximization

Accurately identifying potential purchasers is critical for maximizing profitability in highly competitive markets, spanning industries from finance and insurance to telecommunications. This article presents an enhanced deep learning approach for potential purchaser prediction, leveraging an AutoGlu...

Full description

Saved in:
Bibliographic Details
Main Authors: Hashibul Ahsan Shoaib, Md Anisur Rahman, Jannatul Maua, Ashifur Rahman, M. F. Mridha, Pankoo Kim, Jungpil Shin
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Open Journal of the Computer Society
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10930799/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850211409194909696
author Hashibul Ahsan Shoaib
Md Anisur Rahman
Jannatul Maua
Ashifur Rahman
M. F. Mridha
Pankoo Kim
Jungpil Shin
author_facet Hashibul Ahsan Shoaib
Md Anisur Rahman
Jannatul Maua
Ashifur Rahman
M. F. Mridha
Pankoo Kim
Jungpil Shin
author_sort Hashibul Ahsan Shoaib
collection DOAJ
description Accurately identifying potential purchasers is critical for maximizing profitability in highly competitive markets, spanning industries from finance and insurance to telecommunications. This article presents an enhanced deep learning approach for potential purchaser prediction, leveraging an AutoGluon ensemble framework to optimize accuracy and profitability across diverse datasets, including time deposits, health insurance, 5G packages, and credit cards. The proposed AutoGluon-based ensemble integrates neural networks with boosted trees, stacking, and bagging to maximize the Expected Maximum Profit Criterion (EMPC) and deliver consistent predictive performance across datasets. Our model demonstrates superior performance in terms of Area Under the Curve (AUC), EMPC, and top decile lift (TDL) relative to benchmark classifiers. Specifically, for the credit card dataset, the model achieved an AUC of 0.8856, an EMPC of 13.8453, and a TDL of 3.80, marking significant improvements over prior results. Bayesian A/B testing, based on 40 EMPC ranks, further confirms the robustness of our model, with a 98.5% probability of being the best-performing model across datasets. The AutoGluon ensemble consistently outperforms traditional ensemble models, achieving an average rank-adjusted p-value below 0.015 in the Holm post-hoc test, validating its statistical significance. This study underscores the efficacy of deep learning ensembles in cross-industry potential purchaser prediction, providing a scalable, profit-driven approach for enhanced marketing and customer acquisition strategies.
format Article
id doaj-art-cb27b218e3f84811a15cd951df34bb57
institution OA Journals
issn 2644-1268
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Open Journal of the Computer Society
spelling doaj-art-cb27b218e3f84811a15cd951df34bb572025-08-20T02:09:34ZengIEEEIEEE Open Journal of the Computer Society2644-12682025-01-01646847910.1109/OJCS.2025.355237610930799An Enhanced Deep Learning Approach to Potential Purchaser Prediction: AutoGluon Ensembles for Cross-Industry Profit MaximizationHashibul Ahsan Shoaib0https://orcid.org/0009-0004-1212-8690Md Anisur Rahman1Jannatul Maua2https://orcid.org/0009-0006-1130-6621Ashifur Rahman3https://orcid.org/0000-0003-4308-8527M. F. Mridha4https://orcid.org/0000-0001-5738-1631Pankoo Kim5https://orcid.org/0000-0003-0111-5152Jungpil Shin6https://orcid.org/0000-0002-7476-2468Information Technology, St. Francis College, Brooklyn, NY, USASchool of Engineering and Technology, Western Illinois University, Macomb, IL, USADepartment of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka, BangladeshDepartment of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka, BangladeshDepartment of Computer Science and Engineering, American International University-Bangladesh, Dhaka, BangladeshDepartment of Computer Engineering, Chosun University, Gwangju, South KoreaSchool of Computer Science and Engineering, The University of Aizu, Aizu-wakamatsu, JapanAccurately identifying potential purchasers is critical for maximizing profitability in highly competitive markets, spanning industries from finance and insurance to telecommunications. This article presents an enhanced deep learning approach for potential purchaser prediction, leveraging an AutoGluon ensemble framework to optimize accuracy and profitability across diverse datasets, including time deposits, health insurance, 5G packages, and credit cards. The proposed AutoGluon-based ensemble integrates neural networks with boosted trees, stacking, and bagging to maximize the Expected Maximum Profit Criterion (EMPC) and deliver consistent predictive performance across datasets. Our model demonstrates superior performance in terms of Area Under the Curve (AUC), EMPC, and top decile lift (TDL) relative to benchmark classifiers. Specifically, for the credit card dataset, the model achieved an AUC of 0.8856, an EMPC of 13.8453, and a TDL of 3.80, marking significant improvements over prior results. Bayesian A/B testing, based on 40 EMPC ranks, further confirms the robustness of our model, with a 98.5% probability of being the best-performing model across datasets. The AutoGluon ensemble consistently outperforms traditional ensemble models, achieving an average rank-adjusted p-value below 0.015 in the Holm post-hoc test, validating its statistical significance. This study underscores the efficacy of deep learning ensembles in cross-industry potential purchaser prediction, providing a scalable, profit-driven approach for enhanced marketing and customer acquisition strategies.https://ieeexplore.ieee.org/document/10930799/AutoGluon ensembleautomated machine learningcustomer behavior predictiondeep learningpotential purchaser prediction
spellingShingle Hashibul Ahsan Shoaib
Md Anisur Rahman
Jannatul Maua
Ashifur Rahman
M. F. Mridha
Pankoo Kim
Jungpil Shin
An Enhanced Deep Learning Approach to Potential Purchaser Prediction: AutoGluon Ensembles for Cross-Industry Profit Maximization
IEEE Open Journal of the Computer Society
AutoGluon ensemble
automated machine learning
customer behavior prediction
deep learning
potential purchaser prediction
title An Enhanced Deep Learning Approach to Potential Purchaser Prediction: AutoGluon Ensembles for Cross-Industry Profit Maximization
title_full An Enhanced Deep Learning Approach to Potential Purchaser Prediction: AutoGluon Ensembles for Cross-Industry Profit Maximization
title_fullStr An Enhanced Deep Learning Approach to Potential Purchaser Prediction: AutoGluon Ensembles for Cross-Industry Profit Maximization
title_full_unstemmed An Enhanced Deep Learning Approach to Potential Purchaser Prediction: AutoGluon Ensembles for Cross-Industry Profit Maximization
title_short An Enhanced Deep Learning Approach to Potential Purchaser Prediction: AutoGluon Ensembles for Cross-Industry Profit Maximization
title_sort enhanced deep learning approach to potential purchaser prediction autogluon ensembles for cross industry profit maximization
topic AutoGluon ensemble
automated machine learning
customer behavior prediction
deep learning
potential purchaser prediction
url https://ieeexplore.ieee.org/document/10930799/
work_keys_str_mv AT hashibulahsanshoaib anenhanceddeeplearningapproachtopotentialpurchaserpredictionautogluonensemblesforcrossindustryprofitmaximization
AT mdanisurrahman anenhanceddeeplearningapproachtopotentialpurchaserpredictionautogluonensemblesforcrossindustryprofitmaximization
AT jannatulmaua anenhanceddeeplearningapproachtopotentialpurchaserpredictionautogluonensemblesforcrossindustryprofitmaximization
AT ashifurrahman anenhanceddeeplearningapproachtopotentialpurchaserpredictionautogluonensemblesforcrossindustryprofitmaximization
AT mfmridha anenhanceddeeplearningapproachtopotentialpurchaserpredictionautogluonensemblesforcrossindustryprofitmaximization
AT pankookim anenhanceddeeplearningapproachtopotentialpurchaserpredictionautogluonensemblesforcrossindustryprofitmaximization
AT jungpilshin anenhanceddeeplearningapproachtopotentialpurchaserpredictionautogluonensemblesforcrossindustryprofitmaximization
AT hashibulahsanshoaib enhanceddeeplearningapproachtopotentialpurchaserpredictionautogluonensemblesforcrossindustryprofitmaximization
AT mdanisurrahman enhanceddeeplearningapproachtopotentialpurchaserpredictionautogluonensemblesforcrossindustryprofitmaximization
AT jannatulmaua enhanceddeeplearningapproachtopotentialpurchaserpredictionautogluonensemblesforcrossindustryprofitmaximization
AT ashifurrahman enhanceddeeplearningapproachtopotentialpurchaserpredictionautogluonensemblesforcrossindustryprofitmaximization
AT mfmridha enhanceddeeplearningapproachtopotentialpurchaserpredictionautogluonensemblesforcrossindustryprofitmaximization
AT pankookim enhanceddeeplearningapproachtopotentialpurchaserpredictionautogluonensemblesforcrossindustryprofitmaximization
AT jungpilshin enhanceddeeplearningapproachtopotentialpurchaserpredictionautogluonensemblesforcrossindustryprofitmaximization