Brief Course Description
1. Course Title:
Machine Learning and AI in Finance
2. Language of Instruction:
English
3. Course Code:
BAN606028
4. Credits:
3
5. Course Objectives:
This course provides both theoretical foundations and practical skills in applying Machine Learning and AI to banking-finance, integrating concepts from econometrics, statistics, data science, and programming. Students will be introduced to core methods such as regression, probabilistic modeling, neural networks, deep learning, and reinforcement learning, and their applications to derivative pricing, risk management, market analysis, and algorithmic trading. Through real-world case studies and hands-on projects, students will develop the ability to identify financial problems, select appropriate machine learning tools, and critically assess their effectiveness compared to traditional econometric approaches. The course emphasizes critical thinking, innovation, data analysis, and teamwork skills. By the end of the course, students will be able to confidently apply machine learning techniques to complex financial challenges and contribute to innovation in FinTech and modern financial markets.
6. Brief Description of Course Content:
This course combines theory and practice begins with the foundations of machine learning and artificial intelligence in finance, highlighting big data, FinTech, and the shift from traditional econometrics to data-driven models. Early chapters introduce probabilistic modeling, Bayesian vs. frequentist inference, and Gaussian processes for financial prediction and derivative pricing. Students then study neural networks, feedforward, Bayesian, and deep learning, alongside interpretability methods to address the “black-box” challenge. The second part focuses on sequential data: time-series models (AR, GARCH, Box–Jenkins), probabilistic sequence models (HMMs, state-space, particle filters), and advanced neural networks such as RNNs, LSTMs, GRUs, CNNs, and autoencoders applied to trading, volatility, and cryptocurrency prediction. The final part covers reinforcement learning, from fundamentals (MDPs, Q-learning, Deep RL) to applications in option pricing, portfolio optimization, and wealth management. Advanced topics include inverse reinforcement learning, imitation learning, and physics-inspired approaches, preparing students to innovate in FinTech and quantitative finance.