Command Palette

Search for a command to run...

THIRD SEMESTERcoretheorySem 3

MACHINE LEARNING & DEEP LEARNING

CSS 3201

Syllabus

  • 01Introduction: Background Big Data-Big Compute in Finance, Fintech, Machine Learning and Prediction, Entropy, Neural Networks, Statistical Modeling vs. Machine Learning, Modeling Paradigms, Financial Econometrics and Machine Learning, Over-fitting, Reinforcement Learning, Examples of Supervised Machine Learning in Practice, Algorithmic Trading, High-Frequency Trade Execution, Mortgage Modeling
  • 02Data Preprocessing for Finance- Financial Data Types: Stock prices, time series, high-frequency data, sentiment analysis data; Data Cleaning and Transformation: Handling missing data, Outlier detection, Feature scaling; Feature Engineering for Finance, Feature selection techniques, Domain-specific feature engineering for financial datasets
  • 03Supervised Learning Algorithms in Finance- Regression Models: Linear and Logistic Regression for financial prediction; Decision Trees and Random Forests: Risk modeling and credit scoring, Support Vector Machines: Fraud detection and classification, Evaluation Metrics for Finance: AUC, ROC, Precision, Recall, Sharpe ratio
  • 04Unsupervised Learning in Finance-Clustering Techniques: K-means, Hierarchical Clustering, DBSCAN for market segmentation; Dimensionality Reduction: PCA, LDA for portfolio optimization and risk management, Anomaly Detection: Fraud detection and outlier identification in finance
  • 05Risk Modeling and Credit Scoring- Risk Models: VaR, Expected Shortfall for risk assessment; Credit Scoring Techniques: Logistic Regression, Decision Trees, and Random Forests for risk modelling
  • 06Anomaly Detection and Fraud Detection- Anomaly Detection in Financial Transactions: Identifying suspicious transactions using ML. Evaluation Metrics: Confusion matrix, precision, recall, F1-score
  • 07Time Series Forecasting- Time Series Analysis: AR, MA, ARMA, and ARIMA models for stock price prediction
  • 08Deep Learning in Financial Applications- Deep Learning Fundamentals: Neural networks, CNNs, RNNs, and LSTMs; Application of Deep Learning in Finance: Sentiment analysis using CNN, Fraud detection using autoencoders, Portfolio optimization using deep reinforcement learning
  • 09Sentiment Analysis in Finance-Natural Language Processing (NLP) in Finance: Text mining and sentiment analysis from financial news and social media. RNNs for Sentiment Analysis: Building sentiment analysis models using RNNs or LSTMs to predict market movements
  • 10LSTM and RNN in Financial Time Series: Predicting stock prices using deep learning; Volatility Modeling: GARCH models for financial volatility estimation

References

  • Bryan T. Kelly, Dacheng Xiu, FINANCIAL MACHINE LEARNING, SSRN, July 2023
  • Matthew F. Dixon, Igor Halperin, Paul Bilokon, MACHINE LEARNING IN FINANCE FROM THEORY TO PRACTICE, Springer Nature Switzerland AG, 2020
  • M. Narasimha Murty & V. Susheela Devi, INTRODUCTION TO PATTERN RECOGNITION AND MACHINE LEARNING, World Scientific Publishing Co. Pvt. Ltd. 2015
  • Marcos Lopez De Prado, ADVANCES IN FINANCIAL MACHINE LEARNING, John Wiley & Sons, Inc., Hoboken, New Jersey publication, 2018
  • Yves Hilpisch, PYTHON FOR FINANCE MASTERING DATA-DRIVEN FINANCE, O'Reilly Media Publication, Second Edition, 2020
  • Luigi Troiano, Arjun Bhandari, Elena Mejuto Villa, HANDS-ON DEEP LEARNING FOR FINANCE, Packt Publishing Ltd. Publication, 2020
  • Pradeep Singh, FUNDAMENTALS AND METHODS OF MACHINE AND DEEP LEARNING ALGORITHMS, Tools and Applications, Scrivener Publishing LLC, 2022
  • Trevor Hastie, Robert Tibshirani, and Jerome Friedman, THE ELEMENTS OF STATISTICAL LEARNING, Springer Series in Statistics, 2009
  • Ian Goodfellow, Yoshua Bengio, Aaron Courville, DEEP LEARNING, The MIT Press, 2016
Credits Structure
4Lecture
0Tutorial
0Practical
4Total