Algorithm for cryptocurrency price discrepancy detection

Mínguez Camacho, Daniel (2020). Algorithm for cryptocurrency price discrepancy detection. Thesis (Master thesis), E.T.S. de Ingenieros Informáticos (UPM).

Description

Title: Algorithm for cryptocurrency price discrepancy detection
Author/s:
  • Mínguez Camacho, Daniel
Contributor/s:
  • Lendak, Imre
  • Patiño Martínez, Marta
  • Tyukodi, Gergely
Item Type: Thesis (Master thesis)
Masters title: Data Science
Date: 2020
Subjects:
Faculty: E.T.S. de Ingenieros Informáticos (UPM)
Department: Lenguajes y Sistemas Informáticos e Ingeniería del Software
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (2MB) | Preview

Abstract

As a result of the increasing usage of Bitcoin and other cryptocurrencies as investment and speculative assets, many marketplaces have emerged offering trading services, as well as price aggregators. Different research papers have analysed cryptocurrency prices in general and Bitcoin prices in particular. One common factor of most of them is that they use data extracted from a small subset of marketplaces or even one alone, so the results obtained are only applicable to a subset of the market. It is needed to test whether these results can be generalized by applying the same methods to the rest of the market. This Master Thesis tries to address this problem by making a first step towards the creation of a dataset combining prices from different exchanges to the lowest time precision possible. This lower time precision data is more difficult to obtain due to the fact that marketplaces only offer it in a close to real time manner. A method is described throughout this document, together with the limitations encountered, in order to construct such dataset with data of the pair eth-btc between 31-05-2020 and 02-06- 2020. An analysis is provided regarding the information obtained and possible price discrepancies detected across exchanges. Finally, a machine learning model already used in similar scenarios is implemented in an attempt to predict such discrepancies.

More information

Item ID: 64889
DC Identifier: http://oa.upm.es/64889/
OAI Identifier: oai:oa.upm.es:64889
Deposited by: Biblioteca Facultad de Informatica
Deposited on: 22 Oct 2020 06:40
Last Modified: 22 Oct 2020 06:40
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM