Email this article 
An Efficient Supply Chain Data Warehousing Model For Big Data Analytics
Abstract
This research work is aimed at developing a supply chain data warehousing model for big data analytics that will be used for reporting and analysis purposes. Objected-Oriented Design methodology was adopted for the study. A big data supply chain dataset of a retail outlet from a real world business transaction was used for data analysis. Google storage bucket was created in Google BigQuery for storage and analysis of the data. Data was uploaded into Google storage in the cloud, after which the supply chain data table was created using SQL query. Star Schema dimensional model was created for integrating data into the cloud. For descriptive and diagnostic analytics including feature engineering, the integrated datasets, advanced feature engineering techniques were applied to create derived variables that enhanced the model interpretability and predictive power. Google big Query was linked to Google collab for big data analytics, after which a preliminary analysis was conducted in Google collab showing the first row of the dataset. There was then a decomposition of the time series analysis into trend, seasonality, residuals and original. To perform predictive analytics, the processed dataset was split into training and test datasets to prevent over-fitting. To optimize the model performance, the hyperparameters were adjusted. The forecasting model was implemented within the dashboard using ARIMA and Prophet time series forecasting methods in training the models; and Random forest regression machine learning model in order to implement the most important features that drives sales as well as demand. MAPE and RMSE were used as model evaluation metrics for the predictive analytics of the proposed model. After cross validation of the performance metrics, the study revealed that incorporating advanced Prophet, ARIMA and Random Forest models enhanced the predictive capabilities of the proposed system, leading to more precise inventory management. In conclusion, the proposed system offers better improvements with respect to reliability, performance, scalability, and recoverability because it is designed to handle complex, large scale data operations which are very crucial in modern business environments. The proposed supply chain data warehousing model for big data analytics is highly recommended for supply chain management/managers in inventory management, as the model will help in optimizing the inventory levels as well as improving the supply chain business.
Keywords: Supply Chain, Data Warehousing, Big Data, Analytics
Keywords
Full Text:
PDFReferences
. Lee, I., & Mangalaraj, G. (2022). Big data analytics in supply chain management: A systematic Literature Review and Research directions.
Big Data Cognitive. Computing, 6(17)
. Awwad, M. H., Kulkarni, P., & Bapna, R. (2018). Big data analytics in supply chain: a literature review. Proceedings of the International
conference on Industrial Engineering and Operations Management, September, 27-29.
. Saeid, S. D., Iman, R. V., Farzaneh, M. M. (2020). Big Data Analytics and its Applications in Supply Chain Management. New Trends in
the use of Artificial Intelligence for the Industry 4.0. DOI: http://dx.doi.org/10.5772/intechopen.89426
. Vidhya, K. & Shanmugalakshmi, S. (2020). Modified adaptive neuro – fuzzy inference system (M – ANFIS) based multi-disease analysis of healthcare Big. Journal of Supercomputing, 012345689: 1-22.
. Merceedi, J. K., Yazdeen, A. A., Ibrahim, A. K., Abdulrazzaq, M. B. & Mahmood, M. R. (2022). Analysis of the performance of data
warehouse architecture types. Journal of Soft Computing and Data Mining, 3(1): 45-57.
. Ghuman, B. (2023). What are the key challenges and opportunities for data warehouse optimization in the era of AI and ML? Data
Warehouse Architecture https://www.linkedin.com/advice/0/what-key-challenges-opportunities-data
. Saxena, G. D., Elur, N. R., David, D. S., Kumbhar, S. T. & Premkumar, W. (2022). Picture of data warehouse portrayed with thought for
challenges, modernization and improvement of a conventional data warehouse as well as its possible future perspectives. Journal of
Pharmaceutical Negative Results, 13(9), 8244 -8254.
. Rudniy, A. (2022). Data warehouse design for b ig data in academia. Computers, Materials & Continua, 71(1), 979-992
. Acharjaya, D. & Anitha, A. (2017). A comparative study of statistical and rough computing models in predictive data analysis. Int. Journal
Ambient Computing Intelligent, 8(2), 32-51.
. Agapito, G., Zucco, C. & Cannataro, M. (2020). COVID-warehouse: a data warehouse of Italian COVID-19, pollution, and climate data. International Journal of Environ. Res. Public Health; 17(15), 1-22.
. Saddad, E., El-Bastawissy, A., Mokhtar, H. M. O. & Hazman, M. (2020). Lake data warehouse architecture for big data solutions. Int.
Journal, Adv. Comput. Sci. Appl.; 11(8), 417-424.
. Stefanovic, N. & Milosevic, D. (2017). Model for big data analytics and management. 7th International Conference of Information Society
and Technology (ICIST), 163-168.
. Vieira, A. A.C., Dias, L. M. S., Santos, M. Y, Pereira, G. A. B. & Oliveira, J. A. (2019). Simulation of an automotive supply chain using big
data. Computers & Industrial Engineering, 137: 106033.
. Kilimci, Z. H., Akyuz, A. O., Uysal, M., Akyokus, S., Uysal, M. O., Bulbul, B. A., & Ekmis, M. A. (2019). An improved demand
forecasting model using deep learning approach and proposed decision integration strategy for supply chain. Hindawi Complexity.
. Amirkhalili, Y. S, Aghsami, A, & Jolai, F. (2020). Comparison of time series ARIMA and support vector regression. International Journal
of Hybrid Information Technology; 13(1): 7-18.
. Abbasimehr, H., Shabani, M., & Yousefi, M. (2020). An optimized model using LSTM network for demand forecasting. Computers &
Industrial Engineering, 143: 106435.
. Guo, L., Fang, W., Zhao, Q., & Wang, X. (2021). The hybrid Prophet-SVR approach for forecasting product time series demand with
seasonality. Computers & Industrial Engineering, 161: 107598.
. Sriram, G. K (2022), Edge computing vs. cloud computing: an overview of big data challenges and opportunities for large enterprise.
International Research Journal of Modernization in Engineering Technology and Science, 4(1):1331 – 1337.
. Hamiche, K., Abouaissa, H., Goncalves, G., & Hsu, T. (2018). A robust and easy approach for demand forecasting in supply chains. IFAC-
PapersOnline, 51(11): 1732-1737.
. Siddiqui, R., Azmat, M., Ahmed, S. & Kummar, S. (2022). A hybrid demand forecasting model for greater forecasting accuracy: the case
of the pharmaceutical industry. Supply Chain Forum: An International Journal, 23(2):124-134.
. Banatia, M. A., Baudry, D., & Louis, A. (2022). Detecting counterfeit products by means of frequent pattern mining. Journal of Ambient
Intelligence and Humanized Computing, 13(1): 3683-3692
. Rayani, A., Lathigara, A. & Mehta, A. (2021). Usage of time series forecasting model in supply chain sales prediction. IOP Conference
Series: Materials Science and Engineering, 1042:012022.
. Ramadhani, P.P., Hadi, S. & Rosadi. R. (2021). Implementation of data warehouse in making business intelligence dashboard development
using PostreSQL database and Kimball lifecycle. International Conference on Artificial Intelligence & Big Data Analytics (ICAIBDA); 88-
. Singh, D. (2014). Big data analytic and mining with machine learning algorithm. International Journal of Information and Computation
Technology. 4(1), 33-40.
. Sharma, R., Mithas, S. & Kankanhalli (2014). Transforming decision-making processes: a research agenda for understanding the impact of
business analytics on organizations. European Journal of Information systems, 23, 433-441
DOI: http://dx.doi.org/10.52155/ijpsat.v43.2.6083
Refbacks
- There are currently no refbacks.
Copyright (c) 2024 Odochi Chinwe-Edozie Iheukwumere
This work is licensed under a Creative Commons Attribution 4.0 International License.