Currently, there is a pressing need to emphasize big data analytics (BDA) within the e-commerce sector. Despite its potential, BDA remains not sufficiently explored, which obstructs both its theoretical and practical advancement. This paper systematically reviews the literature on BDA in e-commerce, offering a comprehensive framework that addresses its definitional aspects, characteristics, types, business values and challenges within the e-commerce context. Furthermore, the paper encourages broader discussions regarding future research challenges and opportunities in both theoretical and practical domains. Overall, the findings provide a thorough understanding of various BDA concepts, offering deeper insights into its diverse applications in e-commerce. In recent years, distributed deep neural networks (DDNNs) and neural networks (NNs) have demonstrated exceptional performance across a wide range of applications. For instance, deep convolutional neural networks (DCNNs) have continuously acquired new and additional features for various tasks in computer vision. Concurrently, a large number of end devices including Internet of Things (IoT) devices, has expanded significantly. These devices present attractive targets for machine learning applications due to their frequent connection to sensors such as cameras, microphones, and gyroscopes, which record substantial amounts of input data in a streaming mode.This study delineates the architecture of a Distributed Deep Neural Network (DDNN) that encompasses various computational hierarchies, including multiple end devices, edge nodes, and cloud platforms. The proposed concept is recognized for being new due to its belief in two fundamental layers: the convolutional layer and the pooling layer. The primary aim of integrating these two layers is to achieve optimal performance outcomes. Our findings demonstrate that the proposed methodology yields superior results in terms of accuracy and cost-effectiveness, achieving a precision rate of 99% and an economical cost of 25. Consequently, we conclude that these results surpass those reported in recent literature.
Introduction
With the rise of internet technologies like digital sensors and cloud computing, massive amounts of data are generated daily, known as Big Data (characterized by volume, variety, and velocity). Big Data Analytics (BDA) uses predictive analysis on this data to extract insights that improve business performance, especially in e-commerce.
A novel approach in e-commerce leverages Distributed Deep Neural Networks (DDNNs) on cloud computing to handle large, diverse datasets efficiently. DDNNs split deep learning tasks across cloud, edge, and end devices, improving sensor fusion, fault tolerance, data privacy, and reducing communication costs. This distributed setup enables parallel processing using hardware like GPUs and TPUs, enhancing scalability and accuracy in applications such as personalized marketing, product recommendations, fraud detection, and customer segmentation.
The article reviews how big data analytics combined with distributed convolutional neural networks (CNNs) transform e-commerce by enabling more precise predictions and personalized experiences. CNNs, a type of deep learning model, excel at processing visual, text, and audio data through layers (convolutional, pooling, fully connected) to extract features and recognize patterns. They are widely used in e-commerce for tasks like image-based product search, logo detection in social media, and fraud detection.
Key challenges and training techniques for CNNs include data augmentation, dropout, batch normalization, and hyperparameter tuning (such as number of layers, filter size, learning rate) to prevent overfitting and improve model generalization. Frameworks like TensorFlow and Keras simplify building and training deep learning models on large, complex datasets, making deep learning more accessible and efficient for e-commerce applications.
Conclusion
CNNs have broken across their intended domain to influence a wide range of disciplines, including image recognition and object detection [16]. In healthcare, they\'re reconsidering diagnostics and patient care; in automotive diligence and in the realm of particular technology, they made facial recognition a part of our daily lives. The challenges that CNNs face, similar as addressing bias and enhancing fairness, are not just specialized hurdles but also ethical imperatives [17]. As we continue to upgrade these models. In the future, CNNs will only reach greater heights thanks to developments in technology and algorithms [18]. The integration with edge computing and the disquisition of new infrastructures which promises to unleash indeed more capabilities.
The ongoing exploration and development in the field are not just about making CNNs briskly or more effective; it’s about expanding the boundaries of what’s possible. In summary, understanding CNNs is not just about comprehending a technology; it’s about recognizing a dynamic and evolving field that\'s shaping the future of AI [19]. As we stand on the point of new discoveries and inventions, CNNs will really continue to be a driving force in the trip of artificial intelligence [20], profoundly impacting society and cover the way for an unborn replete with possibilities and advancements.
References
[1] Yaqoob, I. Hashem, A. Gani, S. Mokhtar, E. Ahmed, N. Anuar, and A. Vasilakos, ``Big data: From beginning to future, ‘vol. 36, pp. 1231_1247, Dec. 2016.
[2] P.Mikalef, I. O. Pappas, J. Krogstie, and M. Giannakos, Big data analytics capabilities: A systematic literature review and research agenda, ‘vol. 16, no. 3, pp. 547578, Aug. 2018.
[3] P. Maroufkhani, R. Wagner, W. K. W. Ismail and M.Nourani, ``Big data analytics and performance: A systematic Review”, vol. 10, no. 7, p. 226, 2019.
[4] S. Teerapittayanon, B. McDanel and H. T. Kung, \"Distributed Deep Neural Networks Over the Cloud, the Edge and End Devices,\"2017, pp. 328-339.
[5] I. GAMPA KALPANA, 2 V. MADHUKAR “Study on Big data analytics in E-commerce”, Volume IX Issue JANUARY 2024 ISSN: 2366-1313.
[6] H. Mohamed Zakir; S. VinilaJinny,” Convolutional neural networks method for analysis of e-commerce customer reviews”, March 31 2022 Volume 2444, Issue 1
[7] Dssv Prasad RajuNidadavoluVenkat,” A Comparative Analysis of Machine Learning Algorithms for Big Data Applications in Predictive Analytics”, October 2024 12(10):1608-1630.
[8] Chervenak,A.,Foster,I.,Kesselman,C., Salisbury,C.andTuecke,S.(2000). “Thedata grid: Towardsanarchitectureforthe distributed managementandanalysisoflarge scientific datasets. ?Journal ofNetworkand ComputerApplications”, 23(3), pp.187-200.
[9] Snips. (2018). ?Snips — Using Voice to MakeTechnology Disappear.[online]Available at: https://snips.ai/ [Accessed 27 Nov. 2018].
[10] McMahan,B.andRamage,D.(2017). FederatedLearning:CollaborativeMachine Learning without Centralized Training Data[Accessed28Nov.2018].
[11] McMahan,B.,Moore,E.,Ramage,D., Hampson,S.andAguera,B.(2017). Communication-Efficient Learning ofDeep Networks from Decentralized Data.
[12] Bonawitz,K.,Ivanov,V.,Kreuter,B., Marcedone,A.,McMahan,B.andPatel,S. (2017).PracticalSecureAggregationfor Privacy-Preserving Machine Learning.
[13] Openmined.org.(2018).?OpenMined [Accessed 3 Dec. 2018].
[14] Rodriguez,J.(2018).?Technology Fridays: Open MinedPowersFederatedAIUsingthe Block chain [Accessed 3 Dec. 2018].
[15] Cohen,G.,Afshar,S.,Tapson,J.andvan Schaik,A.(2017).EMNIST:anextensionof MNIST to handwritten letters.
[16] IBM.com. (2018). ?Big Data Analytics [Accessed 6 Dec. 2018].
[17] Bernes, J. (2017). ?The AI-First Business Model – Element AI – Medium [Accessed6Dec.2018].
[18] Gupta,O.andRaskar,R.(2018).Distributed learningofdeepneuralnetworkovermultiple agents. ?Journal of Network and ComputerApplications, 116, pp.1-8.
[19] Practical Secure Aggregation for Privacy-Preserving Machine Learning KallistaBonawitz, Vladimir Ivanov, Ben Kreuter,• Karn SethConference Paper Oct 2017
[20] Blueshift.com. (2018). ?The Leading Customer Data Engagement Platform for marketers [Accessed oct24].