Hyper Parameter Classification on Deep Learning Model for Cryptocurrency Price Prediction

Jongyeop Kim, Jongho Seol, Tasnim Akter Onisha, Yiming Ji

Research output: Contribution to book or proceedingConference articlepeer-review

Abstract

Hyperparameter configurations highly affected the accuracy of the deep learning model. This study focuses on finding an appropriate parameter set that can apply to the Long Short-Term Memory (LSTM) and GRU (Gated Recurrent Unit) for cryptocurrency price prediction. The 80% portion of the data set is composed of an Open-high-low-close (OHLC), movement in the price over time, considered a training data set to predict the remaining 20% of OHLC. Our method classified several appropriate hyperparameter sets, leading to a high accuracy in terms of root mean square error (RMSE) on varying conditions, including number of layers, epochs, and batch size.

Original languageEnglish
Title of host publication2023 IEEE/ACIS 8th International Conference on Big Data, Cloud Computing, and Data Science, BCD 2023
EditorsJongwoo Park, Ngo Thi Phuong Lan, Sungtaek Lee, Tran Anh Tien, Jongbae Kim
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages162-169
Number of pages8
ISBN (Electronic)9798350373615
DOIs
StatePublished - 2023
Event8th IEEE/ACIS International Conference on Big Data, Cloud Computing, and Data Science, BCD 2023 - Ho Chi Minh City, Viet Nam
Duration: Dec 14 2023Dec 16 2023

Publication series

Name2023 IEEE/ACIS 8th International Conference on Big Data, Cloud Computing, and Data Science, BCD 2023

Conference

Conference8th IEEE/ACIS International Conference on Big Data, Cloud Computing, and Data Science, BCD 2023
Country/TerritoryViet Nam
CityHo Chi Minh City
Period12/14/2312/16/23

Keywords

  • Cryptocurrency
  • Deep Learning
  • GRU
  • Input Shape
  • LSTM
  • Machine Learning
  • Price Prediction

Fingerprint

Dive into the research topics of 'Hyper Parameter Classification on Deep Learning Model for Cryptocurrency Price Prediction'. Together they form a unique fingerprint.

Cite this