Impact of Near Real Time Data on Data Science Model Predictions
DOI:
https://doi.org/10.26438/ijcse/v12i4.5560Keywords:
Data Science, Data Quality, Real TimeAbstract
The article delves into an exploration of how the integration of almost real time data streams impacts the accuracy, strength and effectiveness of models, in the ever changing field of data science. groups go beyond boundaries to examine sectors carefully analyzing the effects of data velocity on model performance in industries like finance, healthcare and transportation. Through an investigation the article reveals a story that highlights not the many benefits but also examines the complex challenges involved in utilizing almost real time data for modeling purposes. Additionally the article takes a look at the details discussing the necessary setup requirements and explaining the various methodological approaches needed to seamlessly integrate rapidly updating data streams into existing modeling frameworks. The paper also covers considerations and privacy requirements, for handling data responsibly emphasizing the importance of preserving individual privacy and data integrity. In the end this research acts as a signal emphasizing the importance of utilizing nearly real time data to enhance predictive abilities and drive a significant change in how decisions are made in various fields. This pushes us towards a future of opportunities and transformative possibilities.
References
[1] The Art of Data Science & Big Data Analytics Inspecting & transforming data , Akella Subhadra , Survey Paper | Journal Paper, Jun, Vol.8, Issue.6, pp.91-100, 2020, CrossRef-DOI: , https://doi.org/10.26438/ijcse/v8i6.91100
[2] LONGBING, University of Technology Sydney, Australia, Data Science: A Comprehensive Overview, ACM Computing. Vol.50, Issue.3, pp.1–42, 2017.
[3] Dmitry Ivanov, Omer Ben-Porat, Real-Time Customer Journey Personalization using Online Machine Learning. Published: August 2021.
[4] Pankaj Gupta, "Leveraging Machine Learning and Artificial Intelligence for Fraud Prevention," SSRG International Journal of Computer Science and Engineering, Vol.10, No.5, pp.47-52, 2023. Crossref, https://doi.org/10.14445/23488387/IJCSE V10I5P107
[5] Rahnuma Mahzabin, Fahim Hossain Sifat, Sadia Anjum, Al-Akhir Nayan, Muhammad Golam Kibria, Blockchain associated machine learning and IoT based hypoglycemia detection system with auto-injection feature, Vol.27, No.1, pp.447-455, 2022. Cross Ref-DOI https://doi.org/10.48550/arXiv.2208.02222
[6] Niklas Christoffer Petersen a,b,*, Filipe Rodrigues b, Francisco Camara Pereira b, Multi-output Deep Learning for Bus Arrival Time Predictions, Cross Ref-DOI, Vol.41, pp.138-145, 2019. https://doi.org/10.1016/j.trpro.2019.09.025
[7] Mohamed Medhat Gaber, Arkady Zaslavsky and Shonali Krishnaswamy, Mining Data Streams: A Review , ACM SIGMOD Record, Vol.34, Issue.2, pp.18–26, 2005. https://doi.org/10.1145/1083784.1083789
[8] Xinjun Qi, Mingkui Zong, An Overview of Privacy Preserving Data Mining, Data Privacy challenges, Vol.12, pp.1341-1347, 2012. https://doi.org/10.1016/j.proenv.2012.01.432
[9] J.D. Kelleher, B.M. Namee, A. D’Arcy, “Fundamentals of Machine Learning for Predictive Data Analytics: Algorithms, Worked Examples, and Case Studies” The MIT Press, 2015.
[10] Damiano Perri,Marco Simonetti,Osvaldo Gervasi , Deploying Efficiently Modern Applications on Cloud, Electronics, Vol.11, Issue.3, pp.450, 2022. https://doi.org/10.3390/electronics11030450
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
