Data Mining and Artificial Intelligence for Finance

2022/2023

Учебный год

ENG

Обучение ведется на английском языке

6

Кредиты

Кто читает:

Базовая кафедра инфраструктуры финансовых рынков

Статус:

Маго-лего

Когда читается:

1, 2 модуль

Преподаватели

Теплова Тамара Викторовна

Эмрузнежэд Али

Course Syllabus

Abstract

Aims: Applications of data mining / big data and Artificial Intelligence (AI) are highly useful in today's competitive market. In this course, we introduce data mining and AI techniques that can be applied to financial data. For this purpose, several case studies of well-known data mining techniques are used, e.g. risk analysis in banking, insurance / credit card fraud detection, predicting stock market returns, web analytics and social network analysis including Facebook and Twitter text analytics related to finance. Course Learning Outcomes: Upon successful completion of this course, students will be able to: • Know the advanced techniques of AI and its application to analysis data from financial institutions as well as other decision-making units. • Demonstrate an understanding of the data and resources available on the web of relevance to business intelligence and enable students to access such structured and unstructured data. • Learn advanced data mining and AI methods such as neural networks, clustering, classifications, etc. • Critically analyse the data to real-world problems. • Apply the practical experience and the advanced data mining algorithms needed to reveal patterns and valuable information hidden in large data sets.

Learning Objectives

• The course «Data Mining and AI in Finance» is designed to train specialists in the field of financial data analysis with application of artificial intelligence methods. The aim of the course is to know the advanced techniques of AI and develop skills of data mining for solving problems in the field of risk analysis in banking, insurance /credit card fraud detection, predicting stock market returns, web analytics and social network analysis in finance.

Expected Learning Outcomes

• Know the advanced techniques of AI and its application to analysis data from financial institutions as well as other decision-making units.
• Know the basics of data mining process model for business and management
• Learn advanced data mining and AI methods such as neural networks, clustering, classifications, etc.
• Demonstrate an understanding of the structured and unstructured data and resources available on the web, specially data related to financial institutions that enable students to access and analysis them.
• Critically analyse the data to real-world problems.
• Apply the practical experience and the advanced data mining algorithms needed to reveal patterns and valuable information hidden in large data sets.

Course Contents

• An introduction to data mining process model for business and management and an introduction to Data Mining Package
• Data pre-processing, visualization and exploratory analysis used in business intelligence.
• Use of neural networks in data mining and its application in risk analysis
• Advances in neural networks with an applicant to business intelligence.
• Classification, decision trees and their applications in finance.
• Data mining predictive models and their applications.
• Accessing and collecting data from the web and introduction to text mining.
• Web-analytics and data mining models in real-world applications
• Financial data analysis and modelling using Python
• Clustering, association rules and their applications in Finance
• Advanced data mining techniques and their applications
• Revision, and other AI models applied in finance
• Application of AI to the analysis of sentiment in news and the impact of sentiment on the stock indices.
• Application of AI to the analysis of investor sentiment in social networks and the impact of sentiment on trade characteristics of stocks.

Assessment Elements

• Тест №1 по нейронным сетям
• Тест №2 по методам машинного обучения
• Практическое задание по курсу
• Экзамен

Interim Assessment

• 2022/2023 2nd module
  0.2 * Тест №1 по нейронным сетям + 0.3 * Практическое задание по курсу + 0.3 * Экзамен + 0.2 * Тест №2 по методам машинного обучения

Bibliography

Recommended Core Bibliography

• Artificial intelligence : the basics, Warwick, K., 2012
• Artificial intelligence in economics and management, , 1987

Recommended Additional Bibliography

• A guided tour of artificial intelligence research. Vol. 1: Knowledge representation, reasoning and learning, , 2020
• A guided tour of artificial intelligence research. Vol. 2: AI algorithms, , 2020
• A guided tour of artificial intelligence research. Vol. 3: Interfaces and applications of artificial intelligence, , 2020
• Machine learning : beginner's guide to machine learning, data mining, big data, artificial intelligence and neural networks, Trinity, L., 2019