Editorial: Applications of AI and Machine Learning in Finance and Economics

Introduction

The rapid evolution of AI and Machine Learning is driving a major transformation in finance and economics, enabling real-time data processing, improved decision-making, and advanced risk management. This Research Topic, developed in partnership with the Women in FinTech and AI 2024 conference and MSCA Industrial Doctoral Network on Digital Finance (Grant agreement No: 101119635), highlights cutting-edge research reshaping how we understand and operate in financial markets. The articles included in this Research Topic shed some light in a number of areas where finance, advanced statistical models, and economics are facilitating AI and ML to make significant contributions.

Big Data Analytics in Finance: The enormous increase in data production has opened up huge potential in financial analysis. Today, complex patterns in the huge volumes of data can now be processed and interpreted by advanced ML algorithms to allow us to gain insights about the market sentiment, economic indicators, systemic risks, as well as other factors that a traditional analysis cannot pick up. This Research Topic illustrates this point through compelling contributions such as “Predicting the Bitcoin’s price using AI” (Cohen and Aiche) explores the application of AI and ML in predicting Bitcoin price fluctuations and designing adaptive strategies. This research highlights how these technologies are becoming essential to ensuring stability and unearthing opportunities in an increasingly interconnected global market.

Natural language processing in economic analysis: The use of NLP in understanding financial text, news items, socio-emotional information, and regulatory reports is changing the way we understand financial markets and the economic story. This Research Topic presents fascinating research in this area, including contributions such as articles on “.[–>Does business news sentiment matter in the energy stock market? Globalization and the proliferation of sentiment analysis in extracting short-term stock market prediction” (Lee and Anderl) describes how sentiment analysis has proven to be an efficient analysis method in making short-term stock market predictions for the energy industry, which is considered a volatile market.[–>NLP-augmented inflation measurement with BERT and web scraping” (Berki et al.) show how trans-based models can effectively classify product data, monitor inflation in a near real-time setting based on unstructured text, and enrich established indicators with new dimensions of information.

Digital Finance and Sustainability: One particularly promising area lies at the intersection of sustainable finance and artificial intelligence. Machine learning tools are increasingly being applied to evaluate commodity recycling, assess environmental, social, and governance (ESG) factors, optimize green investment portfolios, and design innovative financial products that support advancing sustainable development goals. Articles in this Research Topic explore the role of this integration in meeting the growing needs of responsible finance by using technology to measure and manage sustainability risks and opportunities. In addition, the study also covers several specialized areas such as ‘.[–>AI revolution in insurance: bridging research and reality” (Bhattacharya et al.) has already covered all the important aspects of this field (auto, health, general insurance). This is because this field is ready to be explored as an innovative and environment-friendly field.

AI-powered financial markets: Intelligent portfolio management systems, robo-advisors, and algorithmic trading are transforming the way financial markets operate. The system not only enables ordering, digital information processing, and trade execution in areas where human traders could never operate at such speed and scale, but also takes into account complex risk tolerances and regulatory restrictions. In this selection,[–>Explainable machine learning to predict the cost of capital (Bussmann et al.) address the most salient issue of these innovations, namely the interpretability of AI financial estimates, and in this article[–>Predicting financial distress in TSX-listed firms using machine learning algorithms (Lokanan and Ramzan) are concerned with more applied issues of risk assessment. Such research demonstrates how innovation can lead to more efficient price discovery, better liquidity levels, and better market access without compromising transparency and regulatory compliance.

Blockchain and distributed ledger applications: The combination of AI and blockchain is opening up new opportunities to conduct secure, transparent, and efficient financial transactions. Artificial intelligence-based smart contracts have the potential to automate more sophisticated financial agreements, and blockchain infrastructure provides the security measures and immutability needed for high-stakes financial processes. This discussion on the challenges of institutional implementation in the form of a qualitative study of boards of directors, including the form of AI and ML in banking systems, is proposed below.[–>Adoption of artificial intelligence and machine learning in banking systems: a qualitative survey of board of directors (Eskandalany).

The role of diversity and inclusion

The partnership of this Research Topic with the conferences Women in FinTech and AI 2024 highlights the issue of diversity and inclusion in promoting innovative changes in the financial technology market. As we continue to see the future of finance entirely revolve around AI and ML, these technological advancements must be developed and implemented by diverse groups, ensuring that we create systems that offer equal benefits to all stakeholders. The article Segmenting female students perceptions about Fintech using Explainable AI (Adam) (winner of the 2024 Best Paper Award) suggests that the use of financial technology (FinTech) is another potential capability to bridge the financial and social gender gap.

Forecasting business cycle and financial indicators

ML and AI are coming to play an important role in the future of finance and economics by providing the techniques to ensure the accuracy of forecasts, at least in the data-impoverished settings. Here, two articles present new ways of predicting GDP in The Gambia, which involves applying sophisticated AI models. The first one, GDP prediction of The Gambia using generative adversarial networks (Jallow, Gibba et al.) uses Generative Adversarial Networks (GAN) with the help of Generative Adversarial Networks for high-accuracy GDP forecasting. the second one,[–>Transfer learning for predicting of gross domestic product growth based on remittance inflows using RNN-LSTM hybrid model: a case study of The Gambia (Jallow, Mwangi et al.) use remittance inflows as the main variable that affects a country in terms of economic growth and use a hybrid version of the RNN-LSTM model with transfer learning. Taken together, these studies highlight the growing importance of AI-driven data-efficient forecasting tools in economic analysis, providing valuable support for policymaking and planning in rapidly developing economies.

Conclusion

The contributions in this Research Topic underscore how AI and machine learning are not merely transforming finance and economics today, but are paving the way for a future characterized by greater financial inclusion, more efficient and transparent markets, and sustainable economic growth. Looking ahead, the continued dialogue between academia, industry, and policymakers will be vital to turning technological advances into meaningful societal progress. As the field evolves, the grand challenge will be to harness innovation responsibly—ensuring that breakthroughs in AI and FinTech are guided by ethical principles and inclusivity, so that the benefits of this new financial era are shared broadly and equitably.