Tyshchenko Svitlana, PhD (Pedagogy), Head of the Department of Economic Cybernetics, Computer Sciences and Information Technologies, Mykolayiv National Agrarian University, Mykolayiv, Ukraine

ORCID ID: 0000-0001-7881-8740
e-mail: tyschenko@mnau.edu.ua

Parkhomenko Oleksandr, PhD (Physics and Mathematics), Associate Professor of the Department of Economic Cybernetics, Computer Sciences and Information Technologies, Mykolayiv National Agrarian University, Mykolayiv, Ukraine

ORCID ID: 0000-0002-7940-7414
e-mail: parkhomenko@mnau.edu.ua

Hilko Ivan, Senior Lecturer, Department of Economic Cybernetics, Computer Science and Information Technology, Mykolaiv National Agrarian University, Mykolaiv, Ukraine

ORCID ID: 0000-0001-7983-8276
e-mail: hilko@mnau.edu.ua

Modeling the Impact Of Digital Threats on Financial Markets Using Time Series Analysis and Anomaly Detection Using Python

Abstract. Introduction. In the digital age, financial markets are becoming increasingly vulnerable to various cyber threats and digital risks. Timely detection and analysis of the impact of such threats on financial markets is critical to minimise potential negative consequences and ensure the stability of the financial system. This study presents an approach to modelling and analysing the impact of cyber threats on financial markets by combining time series analysis, anomaly detection methods, and Python programming tools.

The main objective of this study is to develop a methodology for modelling and analysing the impact of cyber threats on financial markets by integrating time series analysis methods, anomaly detection algorithms and Python implementation.

Results. The study presents a methodology that combines statistical and machine learning techniques for time series analysis and anomaly detection. The methodology includes data preprocessing, trend detection and deseasonalisation of time series, anomaly detection using a combination of statistical and machine learning methods, anomaly analysis and classification, and validation and interpretation of results. The implementation uses Python and powerful libraries such as Pandas, NumPy, Scikit-learn, StatsModels, and TensorFlow/Keras. An example of implementing an anomaly detection algorithm based on Isolation Forest to identify potential digital threats by analysing time series of financial data is presented. Examples of the use of clustering algorithms (K-Means and DBSCAN) for anomaly detection, as well as a combination of the statistical method ARIMA and the machine learning algorithm Isolation Forest for detecting anomalies in the residuals of predicted values of time series are considered. Empirical testing on real financial data demonstrated the effectiveness of the proposed approach in detecting and predicting the impact of cyber threats. Visualisation and analysis of the detected anomalies allowed us to identify their characteristic features and potential causes related to cyber threats.

Conclusions. The results obtained are of practical importance for increasing the resilience of financial markets to cyber threats and minimising risks. The examples presented in this paper are simplified, and their effective application in real-world scenarios will require additional adjustment of model parameters, data processing, and interpretation of results. The developed software can be used by market participants, regulators, and analysts to timely identify and respond to potential cyber threats that affect financial performance. In addition, the proposed methodology can be adapted for use in other areas where monitoring and analysing time-series data for anomalies is required. Further research could focus on improving methods for detecting and classifying anomalies, integrating additional data sources (e.g., news streams or social media) to better understand the nature of cyber threats, and developing automated systems for preventing and responding to identified threats.

Keywords: digital threats, financial markets, time series analysis, anomaly detection, Python, Cybersecurity, statistical methods, clustering algorithms, data analysis, Isolation Forest, ARIMA.

References:

1. Garita, M. (2020). Applied Quantitative Finance: Using Python for Financial Analysis. Palgrave Pivot.
2. Naik, K. (2019). Hands-On Python for Finance: A Practical Guide to Implementing Financial Analysis Strategies Using Python. Packt Publishing.
3. Jansen, S. (2020). Machine Learning for Algorithmic Trading: Predictive models to extract signals from market and alternative data for systematic trading strategies with Python, Packt Publishing.
4. Tyshchenko S., Parkhomenko O. (2024). Analysis of the Impact of Digital Threats on Financial Markets Using Methods of Probability Theory and Python . Modern Economics, 43(2024), 118-124. DOI: https://doi.org/10.31521/modecon.V43(2024)-16.
5. Yang, J., Zhao, Y., Han, C., Liu, Y., & Yang, M. (2022). Big data, big challenges: risk management of financial market in the digital economy. Journal of Enterprise Information Management, 35, 4/5, 1288-1304. https://doi.org/10.1108/JEIM-01-2021-0057.
6. Ahsan, M., Nygard, K. E., Gomes, R., Chowdhury, M., Rifat, N., & Connolly J. F. (2022). Cybersecurity Threats and Their Mitigation Approaches Using Machine Learning–A Review. Journal of Cybersecurity and Privacy, 2 (3), 527–555. https://doi.org/10.3390/jcp2030027
7. Kasianova N., Bilychenko M., Severynenko A. (2023). Modeling the digital security of the enterprise. Modern Economics, 39(2023), 54-61. https://doi.org/10.31521/modecon.V39(2023)-08.
8. Kuchmiiova T. (2023). Impact of Digital Technologies on Modern Society: Transformational Aspects. Modern Economics, 41(2023), 67-72. https://doi.org/10.31521/modecon.V41(2023)-10.
9. Samoilenko, Y., Britchenko, I., Levchenko, I., Lošonczi, P., Bilichenko, O., & Bodnar, O. (2022). Economic security of the enterprise within the conditions of digital transformation. Economic Affairs, 67(4). https://doi.org/10.46852/0424-2513.4.2022.28.
10. Sirenko, N., Baryshevska, I., & Melnyk, O. (2022). The genesis of financial market institutionalisation in Ukraine: An international perspective. Scientific Horizons, 24(10), 97–108. https://doi.org/10.48077/scihor.24(10).2021.97-108.
11. Spivakovskyy, S., Kochubei, O., Shebanina, O., Sokhatska, O., Yaroshenko, I., & Nych, T. (2021). The impact of digital transformation on the economic security of Ukraine. Studies of Applied Economics, 39(5). https://doi.org/10.25115/eea.v39i5.5040.
12. Poltorak, A., Volosyuk, Y., Tyshchenko, S., Khrystenko, O., & Rybachuk, V. (2023). Development of directions for improving the monitoring of the state economic security under conditions of global instability. Eastern-European Journal of Enterprise Technologies, 2(13 (122)), 17–27. https://doi.org/10.15587/1729-4061.2023.275834.