Description

About The Book 

AI & Machine Learning in Banking: Models, Systems, and Real-World Financial Applications is a comprehensive guide to understanding how artificial intelligence is transforming the financial industry. Designed for data scientists, engineers, analysts, and financial professionals, this book bridges the gap between advanced technical concepts and practical, real-world banking applications.
Across twenty detailed chapters, the book explores the full lifecycle of machine learning in banking—from the data ecosystems that power analytics to the modeling techniques used for credit risk, fraud detection, collections optimization, and customer intelligence. It explains how to design and deploy modern ML systems using scalable data pipelines, feature stores, MLOps, real-time scoring, and monitoring frameworks. The book also covers essential governance topics such as explainability, fairness, bias detection, and regulatory compliance, offering readers the tools needed to build models that are both accurate and trustworthy.
In addition to conceptual clarity, readers gain hands-on understanding through practical examples, clear workflows, and Python-based demonstrations. Advanced topics such as deep learning, generative AI, graph intelligence, and reinforcement learning are introduced in an accessible, industry-oriented manner.
Whether you are modernizing legacy decision systems, building next-generation risk models, or exploring AI-driven automation, this book serves as a strategic and technical blueprint. It equips readers with the knowledge necessary to create resilient, scalable, and ethical AI systems that drive measurable value across the banking ecosystem.

About The Author 

I am Deepu Komati, a seasoned engineering leader and data scientist with extensive expertise at the intersection of artificial intelligence, machine learning, and financial technology. My professional focus is dedicated to architecting and deploying advanced data-driven solutions that solve complex business problems at scale.
In my current capacity as a Lead Engineer at HCLTech, I am responsible for designing and optimizing next-generation analytics and automation frameworks that enhance operational efficiency across enterprise financial systems. My work spans end-to-end solution engineering—including ML-driven decision systems, cloud-native architecture, and secure data pipelines—leveraging Python, distributed computing, and platforms such as AWS to deliver measurable business impact.
My career trajectory includes strategic roles in threat detection at Amazon AWS Security and the development of high-impact recommendation engines at Flipkart, giving me a strong foundation in high-stakes, data-intensive, and globally scaled environments.
Academically, I hold a Master’s degree in Data Analytics Engineering from George Mason University. I actively contribute to the broader technology community as a speaker at industry forums such as Conf42, where I present on topics related to high-performance FinTech infrastructure and AI-driven risk management. My published work explores innovative domains including machine learning for credit risk, fraud prevention, and the use of type-2 fuzzy logic for explainable and regulation-compliant AI.
I remain committed to advancing modern engineering and AI practices to drive efficiency, trust, and innovation within the financial services ecosystem.