A new method of ensemble learning:  case of cryptocurrency price prediction

Rather, Akhter Mohiuddin

doi:10.1007/s10115-022-01796-0

Cited by 8 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lastly, there are scholarly investigations that employ a combination of text mining and machine learning/deep learning analyses [5]. These studies primarily center on conducting text-mining analyses, and subsequently utilizing machine-learning analyses based on the obtained results.…”

Section: Related Workmentioning

confidence: 99%

“…The limitations of the natural language processing technology utilized in this research are evident as it struggles to accurately capture the meaning and context of specialized terminologies unique to the cryptocurrency market. Several studies have been conducted to evaluate the effectiveness of different machine learning and deep learning models, revealing research accuracy rates ranging from 40% to 70%, indicating the need for improved performance [5], [6]. Additionally, the long-term, time-based prediction nature of this study presents challenges in applying it to the highly liquid cryptocurrency market.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The prediction of Bitcoin price through gold price using long short-term memory model

Choi,

Choi

2024

IJ-AI

View full text Add to dashboard Cite

<span>The majority of research on predicting the price of Bitcoin employs technical methods to enhance long short-term memory models' effectiveness. Although some studies employ different machine learning techniques, such as economic or technical indicators, their precision is inadequate. Thus, this research aims to introduce a model that predicts the price of Bitcoin by utilizing the long short-term memory (LSTM) technique and incorporating gold's economic and technical data as features. The research collected gold and Bitcoin price data from FinanceDataReader for around seven years, from January 1, 2016, to January 22, 2023, consisting of six categories: date, open, high, low, close, volume, and change (based on dollars). The normalized closing price data was trained for 50 epochs, resulting in the loss value reaching close to zero. The model's accuracy was measured by mean squared error, resulting in a score of 0.0004. This study's importance is two-fold: firstly, it can provide cryptocurrency-related businesses with more accurate predictions and improved risk management indicators. Secondly, incorporating economic metrics can address the limitations of overfitting and a single model's poor performance.</span>

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%