Product guide

Financial AI in Practice: Credit, Fraud, and Investment Systems

Financial AI in Practice by Taehun Kim is a hands-on guide to building AI systems for credit, fraud detection, investment, and customer personalization in regulated financial settings. It describes practical projects alongside model explainability, monitoring, compliance, and governance concerns.

At a glance

Covers credit scoring, fraud detection, investment workflows, and customer personalization.
Explains a four-layer approach spanning data assets, modeling, strategy and monitoring, and applications.
Project topics include XGBoost credit scoring, anomaly and graph-based fraud detection, and an LLM-supported investment workflow.
Addresses regulatory constraints, model risk, fair lending, explainability, monitoring, and human review.

Price

$59.99Save 25%

Reference price: ~~$79.99~~

Price checked: Nov 14, 2026

View offer Ahead of Black FridayExplore the selection

Pros and cons

Pros

Brings several major financial AI use cases together rather than focusing on a single modeling task.
Connects model development with deployment, monitoring, explainability, and regulatory considerations.
Includes six appendices covering setup, datasets and features, metrics, regulation, and references.

Technical specifications

8 specifications

Book details
Publisher	Manning Publications
Publication date	November 3, 2026
Language	English
Print length	464 pages
ISBN-10	1633435393
ISBN-13	978-1633435391

Dimensions and installation
Weight listed	15.8 ounces
Dimensions	7.38 x 1.16 x 9.25 inches

Who is it for?

A good fit for

Data scientists and machine-learning engineers building financial applications.
Product owners and financial analysts working with AI in regulated environments.
Readers seeking applied examples across credit, fraud, investing, and personalization.

Less suited to

Readers looking only for a general introduction to AI without financial applications.
Buyers seeking a narrow, single-topic reference on one model or financial use case.

Customer reviews on Amazon

5 / 5 · 1 ratings

5 stars100%100%
4 stars0%0%
3 stars0%0%
2 stars0%0%
1 star0%0%

The available aggregate rating is positive, but it represents only one rating and provides no written feedback. It cannot establish broader reader satisfaction or confirm how useful the book's described financial AI projects are in practice.

Frequently asked questions

What financial AI topics does the book cover?

The listing describes projects for credit scoring, fraud detection, investment decisions, and customer personalization, alongside monitoring and compliance concerns.

Does it include practical technical examples?

Yes. The described projects include an XGBoost credit-scoring pipeline, LightGBM and autoencoder fraud detection, graph-based fraud analysis, and an investment workflow combining machine learning with an LLM news analyst.

Who is the book intended for?

The listing names data scientists, ML engineers, product owners, and financial analysts building AI in regulated environments.

How much reader feedback is available?

The supplied listing shows a single aggregate rating, which is too little evidence to establish a broad or reliable picture of reader experience.