Trade Bitcoin with neural networks

Bitcoin price prediction has been researched with various ideas. Challenges especially the great magnitude change of the price exist in current research. Research related to bitcoin price prediction concentrated on the time-series models like ARIMA and machine learning methods. Among them, deep lear...

Full description

Bibliographic Details
Main Author: Zhang, Xinting
Format: Dissertation (University of Nottingham only)
Language:English
Published: 2021
Online Access:https://eprints.nottingham.ac.uk/66350/
_version_ 1848800319269502976
author Zhang, Xinting
author_facet Zhang, Xinting
author_sort Zhang, Xinting
building Nottingham Research Data Repository
collection Online Access
description Bitcoin price prediction has been researched with various ideas. Challenges especially the great magnitude change of the price exist in current research. Research related to bitcoin price prediction concentrated on the time-series models like ARIMA and machine learning methods. Among them, deep learning models have a comparable performance. Past research related to deep learning seldom focuses on trading, most of them did not give a clear method to transfer model output into holding positions. In this paper, we model the price of Bitcoin with MLP, RNN, and LSTM. Propose an explicit method to transfer the model output into holding positions including classification networks and regression networks. We also propose a novel way to train a model where we call DOL (direct optimizing loss). DOL allows the model to output the next day’s holding position directly and may utilize trading metrics like Sharp Ratio and Total Return to be the loss function. Our results show that LSTM performs better than MLP and RNN, also the proposed DOL may enhance the performance of models at a considerable level.
first_indexed 2025-11-14T20:49:40Z
format Dissertation (University of Nottingham only)
id nottingham-66350
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T20:49:40Z
publishDate 2021
recordtype eprints
repository_type Digital Repository
spelling nottingham-663502023-04-19T15:30:16Z https://eprints.nottingham.ac.uk/66350/ Trade Bitcoin with neural networks Zhang, Xinting Bitcoin price prediction has been researched with various ideas. Challenges especially the great magnitude change of the price exist in current research. Research related to bitcoin price prediction concentrated on the time-series models like ARIMA and machine learning methods. Among them, deep learning models have a comparable performance. Past research related to deep learning seldom focuses on trading, most of them did not give a clear method to transfer model output into holding positions. In this paper, we model the price of Bitcoin with MLP, RNN, and LSTM. Propose an explicit method to transfer the model output into holding positions including classification networks and regression networks. We also propose a novel way to train a model where we call DOL (direct optimizing loss). DOL allows the model to output the next day’s holding position directly and may utilize trading metrics like Sharp Ratio and Total Return to be the loss function. Our results show that LSTM performs better than MLP and RNN, also the proposed DOL may enhance the performance of models at a considerable level. 2021-12-01 Dissertation (University of Nottingham only) NonPeerReviewed application/pdf en https://eprints.nottingham.ac.uk/66350/1/20136269_BUSI4020_2021.pdf Zhang, Xinting (2021) Trade Bitcoin with neural networks. [Dissertation (University of Nottingham only)]
spellingShingle Zhang, Xinting
Trade Bitcoin with neural networks
title Trade Bitcoin with neural networks
title_full Trade Bitcoin with neural networks
title_fullStr Trade Bitcoin with neural networks
title_full_unstemmed Trade Bitcoin with neural networks
title_short Trade Bitcoin with neural networks
title_sort trade bitcoin with neural networks
url https://eprints.nottingham.ac.uk/66350/