AUTOMATION OF DATA ANALYSIS USING ARTIFICIAL INTELLIGENCE METHODS

The article discusses modern approaches to automating data analysis using artificial intelligence (AI) methods. With the rapid growth of data volumes entering various systems, their analysis and processing are becoming a complex task. Automating these processes with AI allows us to increase the efficiency and accuracy of data analysis, minimize the human factor, and speed up decision-making. The article discusses machine learning and deep learning methods used to automate data analysis, as well as examples of their application in various industries, such as finance, medicine, industry, and marketing. Particular attention is paid to the advantages and limitations of existing approaches, as well as prospects for their further development. The article discusses in detail the conditions and methods of research aimed at studying and evaluating the effectiveness of various AI models in automating data analysis. The obtained results are analyzed and prospects for further development of AI technologies in this area are discussed. The study emphasizes the importance of interpretability of AI models, the need to develop new methods that can effectively work with limited and noisy data, as well as reducing the computational costs associated with their use.

1. Reinsel D. The Digitization of the World From Edge to Core / D. Reinsel, J. Gantz, J. Rydning. – 2018. – 28 р.

2. Dermatologist-level classification of skin cancer with deep neural networks / А. Esteva et al // Nature. – 2017. – № 542(7639). – Р. 115-118.

3. Wang F. AI in Health: State of the Art, Challenges, and Future Directions / F. Wang, A. Preininger // Yearbook of Medical Informatics. – 2019. – № 28(01). – Р. 16-26.

4. Kshetri N. Blockchain’s roles in meeting key supply chain management objectives. / N. Kshetri // International Journal of Information Management. – 2017. – № 39. – Р. 80-89.

5. LeCun Y. Deep learning / Y. LeCun, Y. Bengio, G. Hinton // Nature. – 2015. – № 521(7553). – Р. 436-444.

6. UCI Machine Learning Repository. (n.d.). https://archive.ics.uci.edu/ml/index.php, (date accessed: 27.08.2024)

7. TensorFlow: A System for Large-Scale Machine Learning / М. Abadi et al // OSDI. – 2016. – № 16. – Р. 265-283.

8. Mastering the game of Go with deep neural networks and tree search / D. Silver et al // Nature. – 2016. – № 529(7587). – Р. 484-489.

9. Dermatologist-level classification of skin cancer with deep neural networks / А. Esteva et al // Nature. – 2017. – № 542(7639). – Р. 115-118.

10. Bolton, R.J. Statistical fraud detection: A review. / R.J. Bolton, D.J. Hand // Statistical Science. – 2002. – № 17(3). – Р. 235-255.

11. Recent advances and trends in predictive manufacturing systems in big data environment / J. Lee et al // Manufacturing Letters. – 2013. – № 1(1). – Р. 38-41.

12. Jordan M.I. Machine learning: Trends, perspectives, and prospects / M.I. Jordan, T.M. Mitchell // Science. – 2015. – № 349(6245). – Р. 255-260.