Mariya Paskaleva

Dr. Mariya Paskaleva

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 January 2021 in SHS Web of Conferences
Verified
Journal Article
Open access
PDF file
MPMariya Paskaleva
Mariya Paskaleva
ASAni Stoykova
Ani Stoykova
Research background: Financial globalization has opened international capital markets to investors and companies worldwide. However, the global financial crisis has created big volatility in the stock prices that induces a restriction in the reflection of full information. We explore ten EU Member States (France, Germany, The United Kingdom, Belgium, Bulgaria, Romania, Greece, Portugal, Ireland, Spain), and the USA. The explored period is 03.03.2003 - 30.06.2016, as it includes the effects of the global financial crisis of 2008. Purpose of the article: To determine if there is a contagion effect between the Bulgarian stock market and the other examined stock markets during the crisis period and whether these markets are efficient. Methods: Argument Dickey-Fuller Test, DCC-GARCH Model, Autoregressive (AR) Models, TGARCH Model, Descriptive Statistics. Findings & Value added: Our results show that a contagion across the Bulgarian capital market and eight capital markets exist during the global financial crisis of 2008. We register the strongest contagion effects from US and German capital markets to the Bulgarian capital market. The Bulgarian capital market is relatively integrated with the stock markets of Germany and the United States. That is the explanation of why the Bulgarian capital market is exposed to financial contagion effects from the US capital market and the capital markets of EU member states during the crisis period. We register statistically significant AR (1) for the UK, Greece, Ireland, Portugal, Romania, and Bulgaria, and we can define these global capital markets as inefficient.

4 October 2025 in Risks
Verified
Journal Article
Open access
PDF file
MPMariya Paskaleva
Mariya Paskaleva
Ivanka VasenskaIvanka Vasenska
Ivanka Vasenska
Bitcoin’s extreme price volatility presents significant challenges for investors and traders, necessitating accurate predictive models to guide decision-making in cryptocurrency markets. This study compares the performance of machine learning approaches for Bitcoin price prediction, specifically examining XGBoost gradient boosting, Long Short-Term Memory (LSTM), and GARCH-DL neural networks using comprehensive market data spanning December 2013 to May 2025. We employed extensive feature engineering incorporating technical indicators, applied multiple machine and deep learning models configurations including standalone and ensemble approaches, and utilized cross-validation techniques to assess model robustness. Based on the empirical results, the most significant practical implication is that traders and financial institutions should adopt a dual-model approach, deploying XGBoost for directional trading strategies and utilizing LSTM models for applications requiring precise magnitude predictions, due to their superior continuous forecasting performance. This research demonstrates that traditional technical indicators, particularly market capitalization and price extremes, remain highly predictive in algorithmic trading contexts, validating their continued integration into modern cryptocurrency prediction systems. For risk management applications, the attention-based LSTM’s superior risk-adjusted returns, combined with enhanced interpretability, make it particularly valuable for institutional portfolio optimization and regulatory compliance requirements. The findings suggest that ensemble methods offer balanced performance across multiple evaluation criteria, providing a robust foundation for production trading systems where consistent performance is more valuable than optimization for single metrics. These results enable practitioners to make evidence-based decisions about model selection based on their specific trading objectives, whether focused on directional accuracy for signal generation or precision of magnitude for risk assessment and portfolio management.

1 January 2024 in International Journal of Economic Practice and Policy
Verified
Journal Article
Open access
PDF file
MPMariya Paskaleva
Mariya Paskaleva
Personal data can be seen as an economic asset generated by the identity and behavior of individuals who are traded in exchange for higher-quality services and products. The volume of stored personal data is increasing rapidly. In the two-sided market mechanism, online platforms act as intermediaries that collect consumer data and sell advertising slots to companies. Using personal data removes information asymmetries and contributes to the efficiency of online transactions. Consumers' lack of self-determination of personal data can lead to the uneven exchange of economic value. Unless appropriate measures are taken, such concerns about how data is used threaten to reduce individuals' willingness to share their personal information. Personal data can help businesses perform 'churn detection', identifying customers more likely to leave a retailer. Using such techniques, companies can implement marketing actions to increase customer loyalty. Detecting customer churn is important for businesses because the cost of retaining existing customers is usually lower than the cost of acquiring new customers. Targeted Internet advertising plays a useful informational role for users, as they can see adverts relevant to their potential unique interests. Voluntary data sharing by users is accompanied by explicit rewards and other promotional offers In the current study we explore the advertisements by the online platforms and their relation with personal data transfer. To explore the economic value of personal data, we apply a survey. Correlation analysis is applied.

18 September 2025 in Journal of Tax Reform
Verified
Journal Article
Open access
MPMariya Paskaleva
Mariya Paskaleva
ASAni Stoykova
Ani Stoykova
The digital transformation of the global economy has fundamentally challenged established principles of international taxation, creating urgent demands for policy reform that aligns tax systems with the realities of digital business models. This study presents an empirical evaluation of a four-factor formulary apportionment system (FAS) as an alternative to current transfer pricing mechanisms for taxation in the digital economy. A quantitative simulation methodology is applied to assess redistributive effects and implementation characteristics across twelve representative jurisdictions. The research employs a controlled experimental design using user participation, digital sales, digital assets, and R&D activities as allocation factors, with equal baseline weights of 25% applied to a standardized global profit pool of $50 billion. The analysis includes a baseline impact assessment, sensitivity testing of factor weights, and a comparison with alternative taxation approaches, such as transfer pricing regimes, sales-only formulas, and simplified OECD Pillar One models. Empirical results reveal substantial redistributive effects under the four-factor system, with tax base reallocations ranging from gains exceeding 180% to losses approaching 40%. The findings demonstrate a systematic reallocation from low-tax jurisdictions benefiting from current profit-shifting practices toward market jurisdictions with substantial user bases, sales presence, and economic substance. Sensitivity analysis across seven weighting scenarios reveals that jurisdictions are highly responsive to the user factor, confirming its critical role in digital value creation. These results provide strong empirical support for reforming international tax rules by integrating multi-factor allocation methods that better reflect the borderless and intangible nature of digital business. While offering promising redistribution potential, implementation challenges remain– particularly concerning factor weight stability and global coordination. The study provides quantitative evidence to inform policy debates, suggesting that effective reform necessitates moving beyond incremental changes to adopt comprehensive, formula-based models.

7 February 2025 in Journal of Lifestyle and SDGs Review
Verified
Journal Article
Open access
PDF file
MPMariya Paskaleva
Mariya Paskaleva
Objective: The main objective is to reveal a mechanism for generating sustainable economic growth (SDG 8) by establishing financial stability and enhancing the population's well-being in EU countries during this period of increasing digitalization. Theoretical Framework: This topic presents the main concepts and theories that underpin the research. [List relevant theories, models, or frameworks] stand out, providing a solid basis for understanding the investigation's context. Method: Text mining by VOSViewer is applied. For this analysis, literature sources from the Web of Science database were gathered for the period from 2016 to 2023 because the digital revolution reshaped the economic landscape during this period. To examine the impact of digitalization on economic growth, panel research was conducted, covering 27 European Union member states, using a Vector Autoregression Model. Results and Discussion: Digitization can have a positive impact if there is complete interaction between the implementation of digital technologies and other components of economic development. When advanced solutions are employed to automate tasks without further developing other aspects, achieving economic growth through digitization becomes nearly impossible. Additionally, an unfavorable business environment can hinder the speed of digital transformation. Research Implications: To achieve sustainable economic and social development in line with SDG 8 within the European Union, it is crucial to enhance organizational and economic structures, develop technical and material infrastructure, encourage innovation in production, boost the competitiveness of regional enterprises, foster public-private partnerships, invest in human capital development, and maintain social competitiveness. These measures are vital to unlocking the full potential of digitalization and ensuring a smooth and balanced transition in technology, society, and the economy. Investing in human capital development through avenues such as digital skills training, technology education, and research is essential. This promotes a skilled and adaptable workforce capable of meeting the changing demands of the digital age, driving innovation and economic growth. Originality/Value: This study contributes to the literature by emphasizing a distinct trend: business models are evolving due to the widespread adoption of ICT and the innovations propelled by the Fourth Industrial Revolution. New technologies such as artificial intelligence are generating significant opportunities for entrepreneurship, particularly in gig and circular economies. The effects of digitalization and its socioeconomic implications have captured the attention of analysts.