Core Course
DF622 – Data-driven Financial Analytics
Course Unit Code: DF622
Type Of Unit: Elective
Level of Course Unit: Graduate
Year of Study: 1
Semester: Semester 3
Number of ECTS Credits: 10
Class Contact Hours: 12
Mode of Delivery
Distance Learning
Prerequisites
Managerial Economics and Statistics
Course Objectives
The purpose of the course is to provide students with the fundamental analytical skills, knowledge and tools for application data-driven analysis to advance decision-making, increase effectiveness, reinforce risk management capabilities, and better anticipate upcoming results.
Upon completion of this course, students will be equipped with the necessary and sufficient knowledge and skills to apply machine learning techniques for financial modelling and analysis.
Learning Outcomes
- Describe the difference between quantitative and qualitative variables, as well as cross-sectional data and time series data. Identify the different types of data sources: existing data sources, experimental studies and observational studies.
- To summarise qualitative data by using frequency distribution, bar charts and pie charts. To summarise quantitative data by using frequency distributions, histograms, frequency polygons, and ogives. To compute and interpret the mean, median, and mode; the range, variance, and standard deviation; percentiles, quartiles, and box-and-whiskers displays; covariance, correlation, and the least squares line; weighted means and the mean and standard deviation of grouped data; the geometric mean.
- To describe supervised machine learning, unsupervised machine learning, and deep learning; to describe overfitting and identify methods of addressing it.
- To apply supervised machine learning algorithms—including penalized regression, support vector machine, k-nearest neighbour, classification and regression tree, ensemble learning, and random forest—and determine the problems for which they are best suited.
- To describe unsupervised machine learning algorithms—including principal components analysis, k-means clustering, and hierarchical clustering—and determine the problems for which they are best suited.
- To describe neural networks, deep learning nets, and reinforcement learning.
- To identify and explain steps in a data analysis project.
- To describe preparing, wrangling, and exploring text-based data for financial forecasting; to describe objectives, methods, and examples of data exploration.
- To describe methods for extracting, selecting and engineering features from textual data; to evaluate the fit of a machine learning algorithm
Course Content
1st week:
• Introduction to Business Analytics
2nd week:
• Descriptive Statistics and Analytics: Tabular and Graphic
3rd week:
• Descriptive Statistics and Analytics: Numerical Methods
4th week:
• Financial Time-Series Forecasting
5th week:
• Introduction to Machine Learning in Finance
6th week:
• Supervised Machine Learning Algorithms – 1
7th week:
• Supervised Machine Learning Algorithms – 2
8th week:
• Unsupervised Machine Learning Algorithms – 1
9th week:
• Unsupervised Machine Learning Algorithms – 2
10th week:
• Neural Networks, Deep Learning Nets and Reinforcement Learning
11th week:
• Big Data Projects in Finance
12th week:
• Data preparation and Wrangling. Structured and Unstructured Data
Course Features
Weekly self-assessment activities%):
On a weekly basis, students will have the possibility to engage in self-assessment activities to judge their own level of understanding of the concepts covered so far. The weekly self-assessment activities provide immediate feedback.
Weekly interactive activities (50%):
On a weekly basis, students will have the possibility to interact with the professor, other students, and/or real businesses for the completion of certain activities. These activities are an integral part of the course and help the students comprehend and assimilate the material of each week. Each weekly interactive activity carries 4% of the grade and the professor will provide feedback within 1 week.
Final exam (50%)
The final exam is made up of two parts:
• Part A: Basic Terms and Definitions (multiple-choice questions) – 30 points.
• Part B: Financial Analytics Concepts (essay-type questions) – 35 points.
• Part C: Financial Analytics Calculus (numerical questions) – 35 points.
English (UK) 
Ελληνικά