Forecasting has always been a foundational element in the financial services industry. From projecting economic indicators and modeling credit risk to anticipating stock market trends, the ability to make accurate predictions has long been regarded as a core competitive advantage. Traditionally, financial forecasting relied on classical statistical techniques such as autoregressive models, exponential smoothing, and regression analysis. These approaches, while mathematically rigorous, often assumed linearity, stationarity, and data sufficiency—conditions that do not always hold in the dynamic, complex financial environment of today. Over the past decade, the financial sector has experienced a rapid transformation driven by the convergence of big data, increased computational power, and emerging technologies. Among these, artificial intelligence (AI) has emerged as a revolutionary force. With its capacity to process vast volumes of structured and unstructured data, detect non-linear patterns, and learn from evolving data streams, AI is fundamentally changing how forecasting is conducted. Machine learning (ML), a subset of AI, allows models to continuously improve without explicit programming, making it particularly well-suited to financial environments that are volatile and data-intensive. The emergence of AI in finance has brought both unprecedented capabilities and unique challenges. Financial institutions are now deploying AI systems to forecast market movements, detect fraud in real time, evaluate creditworthiness, and even automate trading strategies. These AI-enhanced forecasting systems are not merely augmenting human decision-making—they are increasingly becoming autonomous agents of analysis and execution. The accuracy, speed, and scalability of AI-driven forecasts are reshaping risk management frameworks, regulatory approaches, and even consumer expectations across the industry. At the core of this transformation lies predictive analytics, a field that combines historical data, statistical algorithms, and ML techniques to identify the likelihood of future outcomes. Predictive analytics is not new to finance, but AI has elevated its utility and precision. Where traditional models were often limited to a few dozen variables, AI systems can ingest thousands of data points—ranging from financial statements and transactional data to social media sentiment and macroeconomic indicators—to generate high-fidelity forecasts. As a result, financial institutions are gaining new tools to address long-standing challenges: improving forecasting accuracy, reducing exposure to unforeseen risks, and enhancing agility in decision-making. The motivation for this research lies in the growing complexity and interconnectedness of global financial systems. As markets become more volatile and data becomes more abundant, the traditional models of forecasting have struggled to keep pace. Events such as the 2008 global financial crisis, the COVID-19 pandemic, and the rise of decentralized finance (DeFi) have demonstrated the limits of historical data in anticipating systemic shocks. In this context, AI and predictive analytics offer a more adaptive and responsive framework for forecasting that accounts for both real-time developments and emerging risks. Moreover, regulatory bodies and stakeholders are increasingly expecting greater transparency and accountability from financial models. This trend is pushing institutions to adopt explainable AI (XAI) methods and to balance predictive power with interpretability. The integration of AI into forecasting also raises important ethical, legal, and operational considerations. Bias in training data, model overfitting, data privacy concerns, and algorithmic opacity are some of the challenges that must be addressed to fully harness the benefits of AI in financial forecasting. This chapter is situated at the intersection of technological innovation and financial strategy, focusing on how AI-powered forecasting tools are reshaping decision-making in the financial sector. The research context spans academic studies, industry applications, and emerging trends in AI adoption across banking, asset management, insurance, and financial technology (fintech). In particular, the chapter draws attention to the contrast between legacy forecasting models and AI-enabled predictive systems, examining their relative strengths, limitations, and strategic implications.
Gatty et al. (Wed,) studied this question.