The programme covers the fundamental knowledge in financial engineering, which is a highly specialised and rapidly growing area. You will be able to explore the computational skills as well as the underlying mathematical and statistical theory to prepare for a career on the computational end of quantitative finance. The programme is both technical and pragmatic. In Mathematical Finance, you will first learn to examine the financial derivatives using a continuous-time approach, then analyse a range of discrete time financial models and investment models. In the 3rd week of the program, you will start the econometric modelling of financial time series. You will learn various methods of fitting linear and non-linear models to time series data, statistical validation and their use such as forecasting and simulation using the statistical package R.
Topic may include:
1) Introduction to stocks/shares and lognormal random walks (including Supply and Demand)
2) Introduction to Portfolios, arbitrage and risk-free investments
3) Introduction to Options/Derivatives (Payoff functions, Rates of Return, and the effects of Gearing)
4) A simple derivation of the Black Scholes equation
5) American vs European options
6) Simple Binomial Methods for determining the value of European/American options
7) Introduction to Path Dependent Options
8) Simple Monte Carlo Methods for determining the value of Path Dependent options
9) Derivative Disasters/LIBOR Scandal/ForEx Scandal
The Lab Sessions will use the MatLAB Software package, which will be fully introduced. You will be expected to implement the Binomial Method and simple Monte Carlo simulations. Dice-rolling games and a Stock Market game will be used to facilitate understanding of concepts of Mathematical Finance. The Class Test will be short and diligent students are expected to pass.
Time Series Analysis
The coverage will be focused on the explorations of the following topics in particular, but not exclusively:
1) Introduction to stationary and non-stationary variables
2) Introduction to Autoregressive distributed lag models and forecasting
3) The Additive Model for a Time Series
4) Linear Filtering of Time Series
5) Autocovariances and Autocorrelations
6) Linear Filters and Stochastic Processes
7) Moving Averages and Autoregressive Processes
8) The Box–Jenkins Program
The Lab Sessions will be based on R. You will be provided introductory material and work on a mini-project which will be presented in on the last day of the module. You will be expected to implement suitable models to analyse a real-world dataset. The oral presentation of the mini-project will be the formal assessment part for the 3rd week.
Please note that the programme plan is subject to confirmation for BISS 2022.