Neural Networks in Finance

Program Type:

Thesis

Non Thesis

Course Code:

FE 625

P:

3

Lab:

0

Credits:

3

ECTS:

10

Course Objectives:

This course is about prediction accuracy with neural networks covering prediction, classification and dimensionality reduction and therefore includes data engineering.

Course Content:

The course content is week by week: Introduction, What are Neural Networks, Estimation of an Evolutionary Computational Network, Evolution of Network Predictions, MATLAB Applications, Artificial Data Forecasting and Estimation, Time Series: Examples from Finance and Industry, Inflation and Deflation: Hong Kong and Japan, Classification : Credit Card Insolvency and Bankruptcies, Dimensionality Reduction and Implicit Volatility Estimation, MATLAB Applications.

Teaching Methods:

1: Lecture, 2: Question-Answer, 3: Discussion, 4: Simulation, 5: Case Study

Assessment Methods:

A: Testing, B: Experiment, C: Homework, Q: Quiz

Vertical Tabs

Course Learning Outcomes

Learning Outcomes	Programme Learning Outcomes	Teaching Methods	Assessment Methods


Understanding and applying network forecasts with financial data	1,2,3,5	1,2,3	A, C
Understanding and applying artificial data estimation and estimation with financial data	1,2,3,5	1,2,3	A, C
Being able to make detailed applications with financial data on various economic issues	1, 5	1,2,3	A, C

Course Flow

COURSE CONTENT
Week	Topics	Study Materials
1	Introduction
2	What are Neural Networks?
3	Estimation of an Evolutionary Computational Network
4	Evolution of Network Predictions
5	MATLAB Applications
6	MATLAB Applications
7	Midterm Exam
8	Estimation and Estimation with Artificial Data
9	Time Series: Examples from Finance and Industry
10	Inflation and Deflation: Hong Kong and Japan
11	Classification: Credit Card Insolvency and Bankruptcies
12	Dimensionality Reduction and Implicit Volatility Estimation
13	MATLAB Applications
14	MATLAB Applications
15	Final

Recommended Sources

RECOMMENDED SOURCES
Textbook			Neural Networks in Finance: Gaining Predictive Edge in the Market, Paul D. McNelis, 2005, Elsevier
Additional Resources			Course Notes Course website, lecture notes, financial markets laboratory, financial calculator, online resources, excel type software.

Material Sharing

MATERIAL SHARING
Documents			Guidelines and additional examples for Lecture Topics and Homework Assignments
Assignments			Homework assignments
Exams			Midterm Exam and Final Exam

Assessment

ASSESSMENT
IN-TERM STUDIES	NUMBER	PERCENTAGE
Mid-Term	1	20
Class Performance	1	20
Final Exam	1	60
	Total	100
CONTRIBUTION OF FINAL EXAMINATION TO OVERALL GRADE		60
CONTRIBUTION OF IN-TERM STUDIES TO OVERALL GRADE		40
	Total	100

COURSE CATEGORY

Expertise/Field Courses

Course’s Contribution to Program

COURSE'S CONTRIBUTION TO PROGRAMME
No	Program Learning Outcomes	Contribution
No	Program Learning Outcomes	1	2	3	4	5
1	To comprehend the basic principles of finance and to be able to apply these principles in national and international areas.					X
2	To use modern information technologies and current financial tools effectively.				X
3	To comprehend the ethical rules and social responsibility understanding accepted by financial professional organizations and to apply them in the decisions to be taken.		X
4	To have the infrastructure that will enable them to do business in multicultural, multilingual and interdisciplinary environments.			X
5	To have information about the markets and the functioning of the markets and to analyze the developments in these markets.			X	X
6	To recognize the management tools and models specific to multinational companies and to be able to apply them where necessary.
7	To understand the structure of the global economic system and to analyze how new developments will affect this structure.		X
8	To be able to use the ability of critical thinking in the decision making process.		X
9	To transfer the acquired leadership, teamwork and communication skills to the lifelong learning process.
10	To be able to manage the process with analytical and creative approaches by anticipating the opportunities and problems that dynamic working conditions may create.

ECTS

ECTS ALLOCATED BASED ON STUDENT WORKLOAD BY THE COURSE DESCRIPTION

Activities	Quantity	Duration (Hour)	Total Workload (Hour)
Course Duration (Including the exam week: 15x Total course hours/week)	16	3	48
Hours for off-the-classroom study (Pre-study, practice, review/week)	16	4	96
Homework	5+1(Proje)	60	60
Mid-term	1	10	20
Final	1	15	30
Total Work Load			254
Total Work Load / 25 (h)			10.16
ECTS Credit of the Course			10

Search form