Hands-On Artificial Intelligence for Banking

Banking decisions involve forecasting, risk, investment, customer behavior, and a great deal of data. Hands-On Artificial Intelligence for Banking explores how machine learning and related AI methods can be applied across these financial settings, moving from an introduction to the field into worked examples and implementation-oriented chapters.

Jeffrey Ng and Subhash Shah connect banking and investment concepts with modeling approaches and tools, giving readers a practical view of where AI techniques may fit into financial applications.

From banking concepts to machine-learning applications

The opening section introduces AI in the finance industry and considers the banking context, including accessible banking, applications of AI, and the potential business impact. The rest of the book turns to examples: time-series analysis for forecasting, machine learning and reinforcement learning for financing decisions, and optimization approaches for capital-market questions.

Explore a broad range of financial use cases

• Forecasting and procurement: time-series methods and neural networks are applied to demand forecasting and commodity procurement.
• Credit and financing: modeling techniques and performance metrics support examples involving bankruptcy-risk prediction and loan funding.
• Investment and portfolios: the book considers capital structure, investor and stock clustering, and portfolio management using the Treynor–Black model and ResNet.
• Sentiment and customer services: topics include market sentiment analysis, graph databases, personal wealth advisers, bank APIs, and chatbot-based client service.

Connect financial reasoning with technical methods

Rather than treating AI as a standalone topic, the examples place modeling choices alongside financial questions. Readers encounter subjects such as risk, financial statements, portfolio returns, and customer wealth, together with machine-learning approaches and practical technology topics including Python, Keras, APIs, and databases.

Who may find it useful?

This book is suited to readers exploring AI applications in banking and finance, including machine-learning and data professionals interested in financial use cases, as well as finance practitioners seeking a clearer view of the techniques. The publisher identifies working knowledge of Python and prior experience with financial markets or banking as prerequisites.

For readers who want to see how data-driven methods meet the varied demands of banking, this book offers a wide-ranging, example-led introduction to the field.