Programme Content
Module 1: Foundations of FinTech & Intelligent Financial Systems
The evolution of FinTech
FinTech Business Model Categories: Payments, Lending, WealthTech, InsurTech, RegTech
Revenue Models in Fintech: Paytm and Zerodha Cases
Mapping FinTech Opportunities: India Stack as a Startup Platform
Core concepts in financial markets, risk, and credit
Introduction to financial datasets: security prices, credit ratings, market data
Module 2: Fintech Concepts and Blockchain
Role of NPCI (National Payments Corporation of India): UPI, IMPS
Mobile Wallets, Payment Gateways and Payment Aggregators: Transactions
Tokenization, Recurring Payments: Risk, Fraud & Failure Scenarios in Recurring Payments
Blockchain and how does it work: When does/does not Blockchain make sense?
Consensus Mechanisms: PoW and PoS
Blockchain Architecture, Smart Contracts
Public vs. Private vs. Consortium Blockchains
Decentralized Finance (DeFi): Decentralized Exchanges (DEXs), AMMs, Decentralized Lending & Over-Collateralization
Module 3: Data Exploration & Visualization for Financial Insights
Introduction to Python
Exploratory Data Analysis (EDA) for structured & unstructured finance data
Data preprocessing: Cleaning, normalization, and feature engineering for financial data.
Visual storytelling with stock market, credit bureau & bank datasets
Hands-on lab: Creating a visual dashboard for financial data
Module 4: Machine Learning Models and Predictive Modeling for Credit & Risk Intelligence (Fintech Application)
Core ML algorithms: Regression, classification, clustering
Applications: Predictive modeling for stock prices and credit scoring
Loan default prediction
Risk analytics for SME lending, credit cards, and personal loans
Model tuning, validation, and bias detection in financial ML models
Use-case lab: Build a regression model for stock price prediction, Build and interpret a credit risk model using real data
Module 5: Algorithmic Trading, WealthTech & Portfolio Analytics
Rule-based and ML-based trading strategies
Backtesting trading signals using Python
Portfolio optimization using Sharpe Ratio, VaR, and Monte Carlo
Robo-advisory engines & personalization of wealth products
Hands-on lab: Simulate and optimize a portfolio allocation strategy
Module 6: AI models for forecasting
AI models for financial analytics: ANN, RNN, CNN
Application in time series forecasting and credit scoring
Evaluating model performance and inference
Hands-on Lab: Train AI models for cryptocurrency price forecasting
Module 7: NLP, Deep Learning & Generative AI in Fintech and Finance
NLP basics: Tokenization, sentiment analysis, topic modeling
Applications in Fintech: Sentiment analysis using news, earnings transcripts, and tweets
Deep learning for time-series: stock movement prediction, fraud detection
GenAI use-cases: financial summarization, Automating investment reports, policy parsing, and KYC
GenAI: Prompt engineering for finance, Risks of hallucination
Use-case lab: Build an NLP model to perform sentiment analysis on financial news, Compare LLM Output with Analysts Note
Module 8: Additional AI applications in FinTech
Fraud detection: Anomaly detection algorithms (Isolation forests)
Regulatory tech (RegTech): AI for compliance
Use-case lab: Fraud detection system using unsupervised learning
Module 9: Capstone Project – Solving Real-World FinTech Challenges
Fraud Detection System for NBFCs
Personalized Investment Recommender
Loan Approval Automation Engine
Wealth Portfolio Optimizer with Predictive Rebalancing
Any other relevant project
