Double-Compressed Artificial Neural Network for Efficient Model Storage in Customer Churn Prediction

Authors

  • Lisang Zhou

    Bazaarvoice Inc., Austin, 78759, TX, United States
  • Huitao Zhang

    Northern Arizona University, Flagstaff, 86011, AZ, United States
  • Ning Zhou

    Zhejiang Future Technology LLC, Hangzhou, 311200, Zhejiang, China

DOI:

https://doi.org/10.30564/aia.v5i2.6377
Received: 2 April 2024 | Accepted: 23 April 2024 | Published Online: 29 April 2024

Abstract

In the rapidly evolving field of Artificial Intelligence (AI), efficiently storing and managing AI models is crucial, particularly as their complexity and size increase. This paper explores the strategic importance of AI model storage, focusing on performance, cost-efficiency, and scalability within the realm of customer churn prediction, utilizing model compression technologies. Deep learning networks, integral to AI models, have become increasingly large, necessitating millions of parameters. These parameters make the models computationally expensive and voluminous in storage requirements. Addressing these issues, the paper discusses the application of model compression techniques—specifically pruning and quantization—to mitigate the storage and computational challenges. The experimental results demonstrated the effectiveness of the proposed method. These techniques reduce the physical footprint of AI models and enhance their processing efficiency, making them suitable for deployment on resource-constrained devices. Using these models in customer churn prediction in telecommunications illustrates their potential to improve service delivery and decision-making processes. By compressing models, telecom companies can better manage and analyze large datasets, enabling more effective customer retention strategies and maintaining a competitive edge in a dynamic market.

Keywords:

Component; Model storage; Model compression; Machine learning; Customer churn prediction

References

[1] Luo, Z., Xu, H., Chen, F.,2019. Audio Sentiment Analysis by Heterogeneous Signal Features Learned from Utterance-Based Parallel Neural Network. In AffCon@ AAAI. pp. 80-87.

[2] Chen, F., Luo, Z., Xu, Y., et al., 2019. Complementary fusion of multi-features and multi-modalities in sentiment analysis. arXiv preprint arXiv:1904.08138.

[3] Luo, Z., Zeng, X., Bao, Z., et al., 2019, July. Deep learning-based strategy for macromolecules classification with imbalanced data from cellular electron cryotomography. In 2019 International Joint Conference on Neural Networks (IJCNN). pp. 1-8.

[4] Qiu, Y., Wang, J., Jin, Z., et al., 2022. Pose-guided matching based on deep learning for assessing quality of action on rehabilitation training. Biomedical Signal Processing and Control, 72, 103323.

[5] Qiu, Y., Yang, Y., Lin, Z., et al., 2020. Improved denoising autoencoder for maritime image denoising and semantic segmentation of USV. China Communications. 17(3), 46-57.

[6] Sun, G., Zhan, T., Owusu, B.G., et al., 2020. Revised reinforcement learning based on anchor graph hashing for autonomous cell activation in cloud-RANs. Future Generation Computer Systems. 104, 60-73.

[7] Qiu, Y., Chang, C.S., Yan, J.L., et al., 2019. Semantic segmentation of intracranial hemorrhages in head CT scans. In 2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS). pp. 112-115.

[8] Shen, Y., Gu, H.M., Qin, S., et al., 2022. Surf4, cargo trafficking, lipid metabolism, and therapeutic implications. Journal of Molecular Cell Biology. 14(9), 63.

[9] Wang, M., Alabi, A., Gu, H.M., et al., 2022. Identification of amino acid residues in the MT-loop of MT1-MMP critical for its ability to cleave low-density lipoprotein receptor. Frontiers in Cardiovascular Medicine. 9, 917238.

[10] Shen, Y., Gu, H.M., Zhai, L., et al., 2022. The role of hepatic Surf4 in lipoprotein metabolism and the development of atherosclerosis in apoE−/− mice. Biochimica et Biophysica Acta (BBA)-Molecular and Cell Biology of Lipids. 1867(10), 159196.

[11] Wang, B., Shen, Y., Zhai, L., et al., 2021. Atherosclerosis-associated hepatic secretion of VLDL but not PCSK9 is dependent on cargo receptor protein Surf4. Journal of Lipid Research. 62.

[12] Deng, S.J., Shen, Y., Gu, H.M., et al., 2020. The role of the C-terminal domain of PCSK9 and SEC24 isoforms in PCSK9 secretion. Biochimica et Biophysica Acta (BBA)-Molecular and Cell Biology of Lipids. 1865(6), 158660.

[13] Shen, Y., Wang, B., Deng, S., et al., 2020. Surf4 regulates expression of proprotein convertase subtilisin/kexin type 9 (PCSK9) but is not required for PCSK9 secretion in cultured human hepatocytes. Biochimica et Biophysica Acta (BBA)-Molecular and Cell Biology of Lipids. 1865(2), 158555.

[14] Xia, D., Alexander, A.K., Isbell, A., et al., 2017. Establishing A Co-Culture System For Clostridium Cellulovorans And Clostridium Aceticum For High Efficiency Biomass Transformation. J. Sci. Heal. Univ. 14, 8-13.

[15] Denker, J., LeCun, Y., 1990. Transforming neural-net output levels to probability distributions. Advances in neural information processing systems, 3.

[16] Denil, M., Shakibi, B., Dinh, L., et al., 2013. Predicting parameters in deep learning. Advances in neural information processing systems. 26.

[17] Zhu, M., Gupta, S., 2017. To prune, or not to prune: exploring the efficacy of pruning for model compression. arXiv preprint arXiv:1710.01878.

[18] Horne, J., Beddingfield, E., Knapp, M., et al., 2020. Caffeine And Theophylline Inhibit Β-Galactosidase Activity And Reduce Expression In Escherichia Coli. Acs Omega. 5(50), 32250-32255.

[19] Mock, M.B., Zhang, S., Pniak, B., et al., 2021. Substrate Promiscuity of The Ndmcde N7-Demethylase Enzyme Complex. Biotechnology Notes, 2, pp.18-25.

[20] Tarca, A.L., Carey, V.J., Chen, X.W., et al., 2007. Machine learning and its applications to biology. PLoS computational biology. 3(6), e116.

[21] Qiu, Y., 2019. Estimation of tail risk measures in finance: Approaches to extreme value mixture modeling (Doctoral dissertation, Johns Hopkins University).

[22] Simonyan, K., Zisserman, A., 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.

[23] Farquad, M.A.H., Ravi, V., Raju, S.B., 2014. Churn prediction using comprehensible support vector machine: An analytical CRM application. Applied Soft Computing. 19, 31-40.

[24] Qiu, Y., Chen, P., Lin, Z., et al., 2020. Clustering Analysis for Silent Telecom Customers Based on K-means++. In 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) .1, 1023-1027.

[25] Tsai, C.F., Lu, Y.H., 2009. Customer churn prediction by hybrid neural networks. Expert Systems with Applications. 36(10), 12547-12553.

[26] Verbeke, W., Martens, D., Mues, C., et al., 2011. Building comprehensible customer churn prediction models with advanced rule induction techniques. Expert systems with applications. 38(3), 2354-2364.

[27] Lu, N., Lin, H., Lu, J., et al., 2012. A customer churn prediction model in telecom industry using boosting. IEEE Transactions on Industrial Informatics. 10(2), 1659-1665.

[28] He, B., Shi, Y., Wan, Q., et al., 2014. Prediction of customer attrition of commercial banks based on SVM model. Procedia computer science. 31, 423-430.

[29] Liu, Z., Sun, M., Zhou, T., et al., 2018. Rethinking the value of network pruning. arXiv preprint arXiv:1810.05270.

[30] Polino, A., Pascanu, R., Alistarh, D., 2018. Model compression via distillation and quantization. arXiv preprint arXiv:1802.05668.

[31] Luo, Z., Xu, H., Chen, F., 2018. Utterance-based audio sentiment analysis learned by a parallel combination of cnn and lstm. arXiv preprint arXiv:1811.08065.

[32] Chen, F., Luo, Z., 2018. Learning robust heterogeneous signal features from parallel neural network for audio sentiment analysis. arXiv preprint arXiv:1811.08065.

[33] Chen, F., Luo, Z., 2019. Sentiment Analysis using Deep Robust Complementary Fusion of Multi-Features and Multi-Modalities. CoRR.

[34] Liu, Y., Bao, Y., 2021. Review of electromagnetic waves-based distance measurement technologies for remote monitoring of civil engineering structures. Measurement. 176, 109193.

[35] Liu, Y., Bao, Y., 2022. Review on automated condition assessment of pipelines with machine learning. Advanced Engineering Informatics. 53, 101687.

[36] Liu, Y., Hajj, M., Bao, Y., 2022. Review of robot-based damage assessment for offshore wind turbines. Renewable and Sustainable Energy Reviews. 158, 112187.

[37] Sugaya, T., Deng, X., 2019. Resonant Frequency Tuning Of Terahertz Plasmonic Structures Based On Solid Immersion Method. 2019 44th International Conference On Infrared, Millimeter, And Terahertz Waves, pp.1-2.

[38] Yu, F., Milord, J., Orton, S., et al., 2021. Students’ Evaluation Toward Online Teaching Strategies for Engineering Courses during COVID. In 2021 ASEE Midwest Section Conference.

[39] Yu, F., Milord, J. O., Flores, L. Y., et al., 2022. Work in Progress: Faculty choice and reflection on teaching strategies to improve engineering self-efficacy. In 2022 ASEE Annual Conference.

[40] Deng, X., Li, L., Enomoto, M., et al., 2019. Continuously Frequency-Tuneable Plasmonic Structures For Terahertz Bio-Sensing And Spectroscopy. Scientific Reports. 9(1), 3498.

[41] Deng, X., Simanullang, M., Kawano, Y., 2018. Ge-Core/A-Si-Shell Nanowire-Based Field-Effect Transistor For Sensitive Terahertz Detection. Photonics. 5(2), 13.

[42] Liu, Y., Liu, L., Yang, L., et al., 2021. Measuring Distance Using Ultra-Wideband Radio Technology Enhanced By Extreme Gradient Boosting Decision Tree (Xgboost). Automation In Construction. 126, 103678.

[43] Yu, F., Strobel, J., 2021. Work-in-Progress: Pre-college Teachers’ Metaphorical Beliefs about Engineering. In 2021 IEEE Global Engineering Education Conference (EDUCON) . pp. 1497-1501.

[44] Kundu, S., Fu, Y., Ye, B., et al., 2022. Toward Adversary-aware Non-iterative Model Pruning through D ynamic N etwork R ewiring of DNNs. ACM Transactions on Embedded Computing Systems. 21(5), 1-24.

[45] Milord, J., Yu, F., Orton, S., et al., 2021. Impact of COVID Transition to Remote Learning on Engineering Self-Efficacy and Outcome Expectations. In 2021 ASEE Virtual Annual Conference.

Downloads

How to Cite

Lisang Zhou, Zhang, H., & Zhou, N. (2024). Double-Compressed Artificial Neural Network for Efficient Model Storage in Customer Churn Prediction. Artificial Intelligence Advances, 6(1), 1–12. https://doi.org/10.30564/aia.v5i2.6377

Issue

Vol. 6 , Iss. 1 (October 2024)

Article Type

Article

License

Copyright © 2024 Lisang Zhou, Huitao Zhang, Ning Zhou

Creative Commons License

This is an open access article under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License.

Crossref
Scopus
Google Scholar
Europe PMC