FINANCIAL TECHNOLOGY
This FINTECH question consists of two components: a theoretical component and a practical component. You are given the choice of employing a concept or a theory in finance, e.g. net present value, financial ratios, risk and return, the capital asset pricing model (CAPM) or others, which you then need to apply to create a MACHINE LEARNING programme using and a graphical user interface (GUI).
For example, if you choose to use the concept of the time value of money, your programme will create a GUI to calculate how much money the customer can earn if they invest their money in a bank with a prevailing interest rate. Basic programming codes will be provided in class. Moreover, standard codes are also available on the Internet and in the Python Standard Library as discussed in class.
You will need to develop your simple programmes individually; however, you may collaborate with your classmates to develop interactive FINTECH and a GUI as discoursed in the discussion forum.
1) Critically discuss a theory in finance. You will then need to apply this theory in the development of your MACHINE LEARNING programme (No.2 below). Hint: this a conceptual question, calculation is not required. Higher marks will be given for rigorous answers with complete Harvard referencing. (25 marks)
2) Develop simple finance programmes, which can be executed using Python and a GUI so your clients can communicate with computers. You are required to send your programmes so I will be able to test them. (25 marks)
Sample Solution
One theory used in finance which can be applied to the development of a Machine Learning programme is the Capital Asset Pricing Model (CAPM). This model identifies the relationship between risk and return for an asset, accounting for systematic risk associated with market movements as opposed to unsystematic risk related to individual securities. The CAPM states that expected returns on any asset are equal to its required rate of return plus a premium calculated by multiplying its beta coefficient and the difference between the expected rate of return on the market and the risk-free rate (Khan & Kumar 2016).
The application of this model in a Machine Learning programme would involve creating a Graphical User Interface (GUI) which takes into account all relevant factors regarding an asset’s performance such as past returns, volatility etc., so as to calculate their future required rate of return based off their beta coefficient along with current market conditions (Fama & French 2020). Additionally it could also provide recommendations on suitable investments based off these calculations by comparing potential options against user specified criteria e.g. time horizons or level of acceptable unsystematic risks associated (Kumar et al., 2018).
In conclusion, CAPM provides useful insights into how different levels of systematic risks impact portfolio diversification; hence it can be applied when developing a Machine Learning programme through creation of GUI which provides guidance related to various assets’ expected rates of returns whilst taking into account external factors such as prevailing market conditions at present.