• Finance professionals and analysts exploring data science
• Aspiring data scientists seeking finance-specific applications
• Business analysts looking to apply machine learning in financial decision-making

• Basic knowledge of finance and statistics
• Familiarity with Python programming
• No prior machine learning experience required

Course Outline:

Module 1: Introduction to Data Science in Finance

• Overview of data science lifecycle
• Key challenges in financial data analysis
• Exploratory data analysis using pandas and matplotlib
• Financial datasets: market data, transactions, credit data
• Hands-on: Cleaning and visualizing financial time-series and tabular data

Module 2: Machine Learning Applications in Finance

• Supervised vs unsupervised learning in finance
• Classification use cases: credit scoring, fraud detection
• Regression use cases: stock price prediction, financial forecasting
• Clustering use cases: customer segmentation and profiling
• Hands-on: Building and evaluating models using scikit-learn
• Hands-on: ROC curves, confusion matrix, R-squared, and error metrics

Module 3: Deep Learning and Advanced Use Cases

• Introduction to neural networks for financial data
• Time-series modeling with LSTM for forecasting
• Anomaly detection using autoencoders
• Use case: Loan default prediction using TensorFlow/Keras
• Hands-on: Deep learning model implementation and evaluation
• Best practices for model deployment and explainability (LIME, SHAP)

Training material provided: Yes (Digital format)