magazinelogo

Advance in Information Technology and Computer Science

ISSN Online: 3066-3156 CODEN:
Frequency: Instant publication Email: AITCS@hillpublish.com
Total View: 73460 Downloads: 6353 Citations: 0 (From Dimensions)
ArticleOpen Access http://dx.doi.org/10.26855/aitcs.2024.12.006

A Lightweight and Interpretable DepGraph-based Pruned Artificial Neural Network for Advertisement Click Prediction

Yu Qiao1, Zhaoyan Zhang2, Alan Wilson3,*

1Meta Platforms, Inc., Bellevue, WA 98005, USA.

2Zhongke Zhidao (Beijing) Technology Co., Ltd., Beijing 102627, China.

3Intact Financial Corporation, Toronto, ON M5G 0A1, Canada.

*Corresponding author: Alan Wilson

Published: December 2,2024

Abstract

The rapid expansion of online advertising has necessitated the development of accurate and efficient models for advertisement click prediction (ACP). Predicting whether a user will click on an ad is crucial for optimizing digital marketing strategies, enhancing user engagement, and maximizing revenue. Traditional machine learning approaches, such as KNN, DT, and GBDT, have been widely used for ACP, but they often require extensive feature engineering and lack adaptability to dynamic user behaviors. While deep learning models, particularly artificial neural networks (ANNs), offer improved accuracy by learning feature representations automatically, they suffer from high computational costs and poor interpretability, limiting their practical deployment. To address these challenges, this study proposes a lightweight and interpretable ACP framework that integrates DepGraph-based pruning with SHAP analysis. By leveraging structured pruning techniques, we significantly reduce the model’s computational overhead while maintaining high predictive performance. The use of SHAP ensures interpretability by identifying key features influencing ad clicks, providing actionable insights for advertisers. Experimental results demonstrate that the pruned ANN model retains strong classification capabilities while achieving a substantial reduction in model size and inference time. Moreover, SHAP analysis highlights the most influential features, such as daily internet usage and time spent on site, which play a crucial role in predicting user engagement. This research presents a scalable and interpretable solution for ACP, making deep learning models more efficient for real-world applications in digital advertising.

Keywords

Advertisement click prediction; model pruning; neural network; SHAP

References

[1] Li C, Tang Y. Emotional Value in Experiential Marketing: Driving Factors for Sales Growth–A Quantitative Study from the Eastern Coastal Region. Econ Manag Inf. 2024 Sep 2:1-3.

[2] Li C, Tang Y. The Factors of Brand Reputation in Chinese Luxury Fashion Brands. J Integr Soc Sci Humanit. 2023 Nov 20:1-4.

[3] Li C. Analysis of Luxury Goods Marketing Strategies Based on Consumer Psychology.

[4] Zhang W, Qin J, Guo W, Tang R, He X. Deep learning for click-through rate estimation. arXiv preprint arXiv:2104.10584. 2021 Apr 21.

[5] Yang Y, Zhai P. Click-through rate prediction in online advertising: A literature review. Inf Process Manag. 2022 Mar 1;59(2):102853.

[6] Regelson M, Fain D. Predicting click-through rate using keyword clusters. In: Proc 2nd Workshop Sponsored Search Auctions; 2006 Jun 11; Vol. 9623. p. 1-6.

[7] McMahan HB, Holt G, Sculley D, Young M, Ebner D, Grady J, et al. Ad click prediction: a view from the trenches. In: Proc 19th ACM SIGKDD Int Conf Knowl Discov Data Min; 2013 Aug 11. p. 1222-30.

[8] Yang Y, Zhai P. Click-through rate prediction in online advertising: A literature review. Inf Process Manag. 2022 Mar 1;59(2):102853.

[9] Li YC, Tang Y. Post-COVID-19 Green Marketing: An Empirical Examination of CSR Evaluation and Luxury Purchase Intention—The Mediating Role of Consumer Favorability and the Moderating Effect of Gender. J Humanit Arts Soc Sci. 2024;8(10):2410-22.

[10] Gan Y, Ma J, Xu K. Enhanced E-Commerce Sales Forecasting Using EEMD-Integrated LSTM Deep Learning Model. J Comput Methods Eng Appl. 2023 Nov 11:1-1.

[11] Wenjun D, Fatahizadeh M, Touchaei HG, Moayedi H, Foong LK. Application of six neural network-based solutions on bearing capacity of shallow footing on double-layer soils. Steel Compos Struct. 2023;49(2):231-44.

[12] Dai W. Design of traffic improvement plan for line 1 Baijiahu station of Nanjing metro. Innov Appl Eng Technol. 2023 Dec 21;10.

[13] Dai W. Safety evaluation of traffic system with historical data based on Markov process and deep-reinforcement learning. J Comput Methods Eng Appl. 2021 Oct 21:1-4.

[14] Xu K, Gan Y, Wilson A. Stacked Generalization for Robust Prediction of Trust and Private Equity on Financial Performances. Innov Appl Eng Technol. 2024 Dec 9:1-2.

[15] Zhang Z. RAG for Personalized Medicine: A Framework for Integrating Patient Data and Pharmaceutical Knowledge for Treatment Recommendations. Optim Appl Mach Learn. 2024 Dec 10;4(1).

[16] Huang W, Ma J. Analysis of Vehicle Fault Diagnosis Model Based on Causal Sequence-to-Sequence in Embedded Systems. Optim Appl Mach Learn. 2023 Sep 12;3(1).

[17] Huang W, Cai Y, Zhang G. Battery Degradation Analysis through Sparse Ridge Regression. Energy Syst. 2024 Dec 10;4(1).

[18] Ma J, Xu K, Qiao Y, Zhang Z. An Integrated Model for Social Media Toxic Comments Detection: Fusion of High-Dimensional Neural Network Representations and Multiple Traditional Machine Learning Algorithms. J Comput Methods Eng Appl. 2022 Nov 2:1-2.

[19] Ma J, Zhang Z, Xu K, Qiao Y. Improving the Applicability of Social Media Toxic Comments Prediction Across Diverse Data Platforms Using Residual Self-Attention-Based LSTM Combined with Transfer Learning. Optim Appl Mach Learn. 2022 Aug 10;2(1).

[20] Ma J, Chen X. Fingerprint Image Generation Based on Attention-Based Deep Generative Adversarial Networks and Its Application in Deep Siamese Matching Model Security Validation. J Comput Methods Eng Appl. 2024 Dec 12:1-3.

[21] Zhou Z, Wu J, Cao Z, She Z, Ma J, Zu X. On-Demand Trajectory Prediction Based on Adaptive Interaction Car Following Model with Decreasing Tolerance. In: 2021 Int Conf Comput Autom (CompAuto); 2021 Sep 7. p. 67-72.

[22] Zhang H, Zhu D, Gan Y, Xiong S. End-to-End Learning-Based Study on the Mamba-ECANet Model for Data Security Intrusion Detection. J Inf Technol Policy. 2024 Sep 7:1-7.

[23] Zhang G, Zhou T. Finite Element Model Calibration with Surrogate Model-Based Bayesian Updating: A Case Study of Motor FEM Model. Innov Appl Eng Technol. 2024 Sep 30:1-3.

[24] Zhu Y, Zhao Y, Song C, Wang Z. Evolving reliability assessment of systems using active learning-based surrogate modelling. Physica D. 2024 Jan 1;457:133957.

[25] Zhao Y, Dai W, Wang Z, Ragab AE. Application of computer simulation to model transient vibration responses of GPLs reinforced doubly curved concrete panel under instantaneous heating. Mater Today Commun. 2024 Mar 1;38:107949.

[26] Fang G, Ma X, Song M, Mi MB, Wang X. Depgraph: Towards any structural pruning. In: Proc IEEE/CVF Conf Comput Vis Pattern Recognit; 2023. p. 16091-101.

[27] Antwarg L, Miller RM, Shapira B, Rokach L. Explaining anomalies detected by autoencoders using Shapley Additive Explanations. Expert Syst Appl. 2021 Dec 30;186:115736.

[28] Gai K, Zhu X, Li H, Liu K, Wang Z. Learning piece-wise linear models from large scale data for ad click prediction. arXiv preprint arXiv:1704.05194. 2017 Apr 18.

[29] Zhang W, Qin J, Guo W, Tang R, He X. Deep learning for click-through rate estimation. arXiv preprint arXiv:2104.10584. 2021 Apr 21.

[30] Pi Q, Zhou G, Zhang Y, Wang Z, Ren L, Fan Y, et al. Search-based user interest modeling with lifelong sequential behavior data for click-through rate prediction. In: Proc 29th ACM Int Conf Inf Knowl Manag; 2020 Oct 19. p. 2685-92.

[31] Ouyang W, Zhang X, Li L, Zou H, Xing X, Liu Z, et al. Deep spatio-temporal neural networks for click-through rate prediction. In: Proc 25th ACM SIGKDD Int Conf Knowl Discov Data Min; 2019 Jul 25. p. 2078-86.

[32] Wang Z, Zhao Y, Song C, Wang X, Li Y. A new interpretation on structural reliability updating with adaptive batch sampling-based subset simulation. Struct Multidiscip Optim. 2024 Jan;67(1):7.

[33] Chen X, Wang M, Zhang H. Machine Learning-based Fault Prediction and Diagnosis of Brushless Motors. Eng Adv. 2024 Aug 6;4(3).

[34] Chen X, Gan Y, Xiong S. Optimization of Mobile Robot Delivery System Based on Deep Learning. J Comput Sci Res. 2024;6(4):51-65.

[35] Chen X, Zhang H. Performance Enhancement of AlGaN-based Deep Ultraviolet Light-emitting Diodes with AlxGa1-xN Linear Descending Layers. Innov Appl Eng Technol. 2023 Oct 31:1-0.

[36] Peterson LE. K-nearest neighbor. Scholarpedia. 2009 Feb 21;4(2):1883.

[37] Zhang Z. Introduction to machine learning: k-nearest neighbors. Ann Transl Med. 2016 Jun;4(11):218.

[38] Larose DT, Larose CD. k-nearest neighbor algorithm.

[39] De Ville B. Decision trees. Wiley Interdiscip Rev Comput Stat. 2013 Nov;5(6):448-55.

[40] Podgorelec V, Kokol P, Stiglic B, Rozman I. Decision trees: an overview and their use in medicine. J Med Syst. 2002 Oct;26:445-63.

[41] Magee JF. Decision trees for decision making. Brighton, MA, USA: Harvard Bus Rev; 1964 Jul 1.

[42] Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, et al. Lightgbm: A highly efficient gradient boosting decision tree. Adv Neural Inf Process Syst. 2017;30.

[43] Zhang Z, Jung C. GBDT-MO: Gradient-boosted decision trees for multiple outputs. IEEE Trans Neural Netw Learn Syst. 2020 Aug 4;32(7):3156-67.

[44] Dev VA, Eden MR. Gradient boosted decision trees for lithology classification. In: Comput Aided Chem Eng; 2019 Jan 1; Vol. 47. p. 113-8.

[45] Gan Y, Chen X. The Research on End-to-end Stock Recommendation Algorithm Based on Time-frequency Consistency. Adv Comput Commun. 2024 Nov 14;5(4).

[46] Zhang G, Zhou T, Cai Y. CORAL-based Domain Adaptation Algorithm for Improving the Applicability of Machine Learning Models in Detecting Motor Bearing Failures. J Comput Methods Eng Appl. 2023 Nov 3:1-7.

[47] Zhang J, Ma X, Zhang J, Sun D, Zhou X, Mi C, et al. Insights into geospatial heterogeneity of landslide susceptibility based on the SHAP-XGBoost model. J Environ Manage. 2023 Apr 15;332:117357.

[48] Wang H, Liang Q, Hancock JT, Khoshgoftaar TM. Feature selection strategies: a comparative analysis of SHAP-value and importance-based methods. J Big Data. 2024 Mar 26;11(1):44.

How to cite this paper

A Lightweight and Interpretable DepGraph-based Pruned Artificial Neural Network for Advertisement Click Prediction

How to cite this paper: Yu Qiao, Zhaoyan Zhang, Alan Wilson. (2024) A Lightweight and Interpretable DepGraph-based Pruned Artificial Neural Network for Advertisement Click Prediction. Advance in Information Technology and Computer Science, 1(1), 22-35.

DOI: http://dx.doi.org/10.26855/aitcs.2024.12.006