Exploration and Study of Effect in Big Data Analytics for Supply Chain Management

Abstract

Big data analytics has become a crucial aspect of modern supply chain management, with the newlineincreasing volume of data generated by Information and Communication Technology (ICT) newlinesupply chains presenting organizations with significant challenges in effectively managing and newlineanalyzing this data. The handling of big tabular data in ICT supply chains requires specialized newlinetechniques for processing and analysis, and this study proposes a multi-task, machineinterpretable newlineapproach for this purpose. This approach involves several key steps, including data newlinepreprocessing, feature engineering, multi-task learning, machine interpretability, and newlineexperiments and analysis. The proposed approach has several key benefits, including improved newlinedecision-making, increased efficiency, better understanding of ICT supply chains, and newlineoptimization and improvement. Additionally, this study also investigates the influencing newlineelements and the impact of big data analytics on supply chain performance. This exploration and newlinestudy of effects in big data analytics for supply chain management aims to provide organizations newlinewith a comprehensive understanding of the potential benefits and challenges associated with the newlineuse of big data analytics in ICT supply chains. newlineUnderstanding how big data analytics has impacted the supply chain for retailers is the primary newlinegoal of this research. We design our framework to choose the finest big data techniques from a newlinerange of options based on the effectiveness of the retailing sector. Researchers used TODIM, newlinewhich stands for Portuguese Interactive Multi-Criteria Making Decisions, to choose the best newlinetools for big data analytics from the nine practices (based on seven supply chain performance newlinecriteria, machine learning, artificial neural, enterprise resource planning cloud services, machine newlinelearning, data mining, RFID, Block chain, and IoT) (supplier integration, customer integration, newlinecost, capacity utilization, flexibility, demand management, and time and value). The analysis of newlinetabular patterns mechanically is essential