Abstract
Every year in the United States, the 4th Thursday of November is commemorated as Thanksgiving Day. The next day which is a Friday is known as Black Friday. This day is the busiest day in terms of shop** because all major retailers and e-commerce websites offer massive amounts of discounts and deals. Hence, this sale is termed the Black Friday Sale. There is a lot of potentials to make a profit even after such discounts if the sales patterns from previous years’ data are analyzed properly. Investigating various demographics of customers and analyzing the purchase amount spent by each customer on various products, there is a need to find out patterns for this behavior. Therefore, we utilized classical and modern artificial intelligence and machine learning techniques such as Linear Regression, Neural Networks, Gradient Boosting Trees and AutoML, to make predictions on the available test data to find a model for the most accurate predictions. We used a Graphical Processing Unit (GPU)-based high-performance computing environment to analyze the performance of various artificial intelligence and machine learning techniques for e-commerce applications. Since the dataset contains information about various demographics and backgrounds of the customers, we encoded the data in an easy-to-understand format and reduce the bias for each algorithm. Furthermore, various techniques of feature engineering are used, and new features are generated from existing features by grou** the target variable purchase, for each sub-category of that feature. Erroneous predictions are also handled; ultimately, the model performed well on unseen test data. Finally, this study can help researchers to find the best model with more accurate predictions for e-commerce applications.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Yi, D. (2010, November 23). Black Friday Deals for Target, H&M, Forever21, Old Navy, Radio Shack, and More. Daily News. New York. Archived from the original on August 15, 2011
Yahoo. (2010, November 23). Black Friday Moves to Thursday as Stores Woo Shoppers. Financially. Yahoo! Finance. Archived from the original on July 26, 2011. Retrieved January 2, 2012,
Chopra, M., Singh, S. K., Aggarwal, K., & Gupta, A. (2022). Predicting catastrophic events using machine learning models for natural language processing. In Data Mining Approaches for Big Data and Sentiment Analysis in Social Media (pp. 223–243). IGI Global.
Hossain, M. S., Uddin, M. K., Hossain, M. K., & Rahman, M. F. (2022). User sentiment analysis and review rating prediction for the blended learning platform app. In Applying data science and learning analytics throughout a learner’s lifespan (pp. 113–132).
Peñalvo, F. J. G., Maan, T., Singh, S. K., Kumar, S., Arya, V., Chui, K. T., & Singh, G. P. (2022). Sustainable stock market prediction framework using machine learning models. International Journal of Software Science and Computational Intelligence, 14(1), 1–15.
Knowledge and Learning. (2016). Practice problem: Black Friday sales prediction | Knowledge and Learning, July 2016. [Online]. Available: https://datahack.analyticsvidhya.com/contest/black-friday/
Iftikhar, S., Ahmad, M. M. M., et al. (2022). HunterPlus: AI based energy-efficient task scheduling for cloud-fog computing environments. Internet of Things, 21, 100667. (pp. 1–17). Elsevier.
Li, P., Li, D., Li, W., Gong, S., Fu, Y., & Hospedales, T. M. (2021). A simple feature augmentation for domain generalization. In IEEE/CVF International Conference on Computer Vision (ICCV). IEEE.
Jain, A.. (2021). Blackfriday-AV, URL: https://www.kaggle.com/amanacden/blackfridayav/notebook. Last Accessed on 27 May 2021.
Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining (pp. 785–794). Association for Computing Machinery.
Dorogush, A. V., Ershov, V., & Gulin, A., CatBoost: Gradient boosting with categorical features support. ar**v preprint ar**v:1810.11363. (2018)
Iftikhar, S., et al. (2023). AI-based fog and edge computing: a systematic review, taxonomy and future directions. Internet of Things, 23, 100674. Elsevier.
Brdesee, H. S., Alsaggaf, W., Aljohani, N., & Hassan, S. U. (2022). Predictive model using a machine learning approach for enhancing the retention rate of students at-risk. International Journal on Semantic Web and Information Systems (IJSWIS), 18(1), 1–21.
Basheer, S., Gandhi, U. D., Priyan, M. K., & Parthasarathy, P. (2022). Network support data analysis for fault identification using machine learning. In Research anthology on machine learning techniques, methods, and applications (pp. 586–595). IGI Global.
Barnston, A. G. (1992). Correspondence among the correlation, RMSE, and Heidke forecast verification measures; Refinement of the Heidke Score. Weather Forecasting, 7(4), 699–709.
Trung, N., Tan, D., & Huynh, H. (2019). Black Friday Sale Prediction Via Extreme Gradient Boosted Trees. [online] Available at: http://vap.ac.vn/proceedingvap/proceeding/article/view/84. Accessed 3 Jan 2023.
Kalra, S., Perumal, B., Yadav, S., & Narayanan, S. J. (2020). Analysing and predicting the purchases done on the day of Black Friday. In International conference on emerging trends in information technology and engineering. IEEE.
**n, S., Ester, M., Bu, J., Yao, C., Li, Z., Zhou, X., et al. (2019). Multi-task based sales predictions for online promotions. In 28th ACM international conference on information and knowledge management. Association for Computing Machinery.
Wu, C. M., Patil, P., & Gunaseelan, S. (2018a). Comparison of different machine learning algorithms for multiple regression on Black Friday sales data. In IEEE International Conference on Software Engineering and Service Science (ICSESS). IEEE.
Ramasubbareddy, S., Srinivas, T. A. S., Govinda, K., & Swetha, E. (2021). Sales analysis on back friday using machine learning techniques. In Intelligent system design: Proceedings of intelligent system design: INDIA 2019 (pp. 313–319). Springer Singapore.
Catboost. (2023). https://catboost.ai/en/docs/concepts/python-reference_catboostregressor, Accessed on 3 Jan 2023.
GridSearchCV. (2023). https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.GridSearchCV.html. Accessed on 3 Jan 2023.
Keras Documentation. (2023). URL: https://keras.io/api/. Accessed on 3 Jan 2023.
Keras EarlyStop**. (2023). URL: https://keras.io/api/callbacks/early_stop**. Accessed on 3 Jan 2023.
H2O AutoML. (2023). URL: https://docs.h2o.ai/h2o/latest-stable/h2o-docs/automl.html. Accessed on 3 Jan 2023.
He, X., Zhao, K., & Chu, X. (2019). AutoML: A survey of the state-of-the-art. Knowledge-Based Systems. ar**v preprint ar**v:1908.00709.
Gill, S. S., Xu, M., Ottaviani, C., Patros, P., Bahsoon, R., Shaghaghi, A., et al. (2022a). AI for next generation computing: emerging trends and future directions. Internet of Things, 19, 100514.
Xu, M., Song, C., Wu, H., Gill, S. S., Ye, K., & Xu, C. (2022). esDNN: deep neural network based multivariate workload prediction in cloud computing environments. ACM Transactions on Internet Technology, 22(3), 1–24.
Gill, S. S., Kumar, A., Singh, H., Singh, M., Kaur, K., Usman, M., & Buyya, R. (2022b). Quantum computing: a taxonomy, systematic review and future directions. Software Practice & Experience, 52(1), 66–114.
Gill, S. S. (2021). Quantum and blockchain based Serverless edge computing: a vision, model, new trends and future directions. Internet Technology Letters, 24, e275.
Abdelmoniem, A. M., Elzanaty, A., Alouini, M.-S., & Canini, M. (2021). An efficient statistical-based gradient compression technique for distributed training systems. Proceedings of the Machine Learning System (MLSys), 3, 297–322.
Abdelmoniem, A. M., & Canini, M. (2021a). Towards mitigating device heterogeneity in federated learning via adaptive model quantization. In ACM EuroMLSys. Association for Computing Machinery.
Xu, H., Ho, C.-Y., Abdelmoniem, A. M., Dutta, A., Bergou, E. H., Karatsenidis, K., Canini, M., & Kalnis, P. (2021). GRACE: A compressed communication framework for distributed machine learning. In IEEE 41st International Conference on Distributed Computing Systems (ICDCS). IEEE.
Abdelmoniem, A. M., Ho, C.-Y., Papageorgiou, P., & Canini, M. (2022). Empirical analysis of federated learning in heterogeneous environments. In ACM EuroMLSys. Association for Computing Machinery.
Abdelmoniem, A. M., & Canini, M. (2021b). DC2: Delay-aware compression control for distributed machine learning. In IEEE conference on computer communications (INFOCOM). IEEE.
Abdelmoniem, A. M., Sahu, A. N., Canini, M., & Fahmy, S. A. (2023). Resource-efficient federated learning, ACM EuroSys. arxiv preprint ar**v:2111.01108.
Acknowledgements
This work is partially funded by Chinese Academy of Sciences President’s International Fellowship Initiative (Grant No. 2023VTC0006), National Natural Science Foundation of China (No. 62102408), and Shenzhen Science and Technology Program (Grant No. RCBS20210609104609044).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Tewatia, S. et al. (2023). GPU Based AI for Modern E-Commerce Applications: Performance Evaluation, Analysis and Future Directions. In: Kumar, M., Gill, S.S., Samriya, J.K., Uhlig, S. (eds) 6G Enabled Fog Computing in IoT. Springer, Cham. https://doi.org/10.1007/978-3-031-30101-8_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-30101-8_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-30100-1
Online ISBN: 978-3-031-30101-8
eBook Packages: Computer ScienceComputer Science (R0)