/CurrencyAnalyser

Final Year Project, based on the idea of analysing and predicting cryptocurrency prices.

Primary LanguageJupyter NotebookMIT LicenseMIT

4th Year Applied Project

An Analysis of the Viability and Volatility of Cryptocurrency with Currency Analyser Web Application

Module: Applied Project and Minor Dissertation / 4th Year Software Development
Team: Rebecca Kane, Tara O'Kelly (Group 3.2)
Supervisor: Dr Ian McLoughlin

Screencast
A screencast of the Currency Analyser web application can be viewed on Youtube, here.
The screencast can also be downloaded from this repository, here.

Jump to
Project Description
Theoretical Aspect
Applied Aspect
Team Partition

Dissertation Abstract

The field of cryptocurrency has enjoyed exponential growth in popularity in recent years. Almost ten years ago, the release of Bitcoin marked the beginning of a new era of innovation in the financial sector. In this dissertation we outline what exactly defines a cryptocurrency, describing fundamental concepts, underlying technologies such as the blockchain, and subsequently the viability of this new digital financial asset. Building on this knowledge, we examine the infamous volatility of cryptocurrency prices, analysing pricing data and the likelihood of these currencies, specifically Bitcoin, being in the midst a financial bubble. We examine the prediction of prices, or rather inability to do so, before introducing the Currency Analyser web application developed as part of this project. Containing up to date prices, this web application is hosted on Heroku for public access and predicts prices of Bitcoin using machine learning. The research planning methodologies, technologies, and design and evaluation of this application are described in detail in the penultimate chapter of this dissertation, followed by a concluding word on the process as a whole.

Project Description

Our project consists of two major components; a theoretical analysis of cryptocurrency, and an applied aspect in the form of a web application.

Theoretical Aspect

The theoretical component of our project is discussed in detail in our dissertation, and focuses on two subjects; understanding cryptocurrency and why it should be considered a viable method of trading, and predicting the prices of cryptocurrency and their associated volatility. We used this format as we believe there still exists a great deal of mystery surrounding cryptocurrency to the average person, and wanted to provide a resource suitable for even the most inexperienced of users.

Understanding Cryptocurrency
In this chapter, we start from the basics of what exactly cryptocurrency is and its underlying technologies. We explain the very beginnings of cryptocurrency back in the 1990s, followed by an introduction to cryptocurrency today. We explain the characteristics of most cryptocurrencies, such as decentralised systems, anonymity, mining and trading cryptocurrency, and how all of this makes cryptocurrency different from traditional currency. We discuss Bitcoin, the most famous (and expensive) of cryptocurrencies and its origins, as well as the innovative technology known as Blockchain that it brought to the world. We then conclude the chapter by summarising the various aspects which make cryptocurrency a viable asset to be traded.

Predicting the Prices of Cryptocurrency
Contrasting the previous chapter, this section outlines how volatile cryptocurrency can be. We will explain what directly and indirectly affects the prices of cryptocurrency, specifically referencing Bitcoin. We then discuss the Bitcoin "Bubble" and the inability to absolutely predict prices of any cryptocurrency, followed by a more upbeat outlook of making educated estimates of price changes and thus introducing our Currency Analyser web application.

Applied Aspect

Our Currency Analyser web application is designed to be used by anyone with any level of knowledge of cryptocurrencies, however it is advised that the user has read and understood Chapter 2 and 3.
Our application provides the user with up-to-date prices of Bitcoin and some major traditional currencies. The most recent values are plotted on a graph, which is updated every 30 seconds.
There is also a prediction feature, which uses the Long Short Term Memory algorithm to estimate the closing price of Bitcoin for the current day. Of course, this model is not ideal for long term prediction and while it can be somewhat accurate for short term prediction, it should not be relied upon due to the volatility of Bitcoin prices.

Team Partition

Original Team: John Glynn, Rebecca Kane, Tara O'Kelly

The team made the collective decision to separate at the beginning of April. While this did come at a crucial stage of the project, all members agreed it was the best option. There were a variety of reasons behind this decision, to be discussed in Chapter 4 of the dissertation, and fortunately all team members are still on amicable terms.

All work prior to 9 April 2018 is considered a collaborative effort and is authorised to be used by either new team. The work of this repository is related to Team 3.2 - Rebecca Kane and Tara O'Kelly.