AI in Finance From Insight to Action
summary
Builds two practical pipelines in Python using scikit-learn and pandas: a monthly‑expense predictor and an unsupervised fraud finder. The expense demo shows a single‑feature linear model fails but a multi‑variable regression on ~500 rows reaches about R² ≈ 0.93. The fraud demo uses K‑means clustering, StandardScaler and t‑SNE/PCA to find three clusters, with two high‑risk patterns — large night transfers and many small high‑activity transactions — then exports cluster features for a supervised model.
AI-written summary · about
chapters (12)
- 0:00AI in finance intro
- 1:23AI/ML fundamentals
- 3:51AI/ML in finance history
- 11:16Traditional finance limits
- 15:51Why AI in finance
- 19:27Monthly expense model
- 27:00Expense forecasting prep
- 31:39Expense data analysis
- 45:30Linear regression evaluation
- 50:53Fraud detection clustering
- 1:02:32Fraud feature extraction
- 1:22:55Q&A
related talks
59mAI in Finance: Scope and Examples- 59mAI in Finance: Scope and Examples
08mAI-Powered Fraud Detection in Financial System
01h 03mAI Innovation for a Smarter Financial Ecosystem
41mAI For All: Enhancing Digital Financial Services using Data Science
38mAI in action: How to use practically in iGaming beyond the hype?
50mKeynote Panel: AI in Finance
19mAI & Digital Twins for Financial Risk & Asset Optimization