Cryptocurrency Price Prediction Using Neural Networks and Deep Learning

Biswas, Sumit; Pawar, Mohandas; Badole, Sachin L.; Galande, Nachiket; Rathod, Sunil

doi:10.1109/icaccs51430.2021.9441872

Cited by 18 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we review the papers predicting the price of cryptocurrencies. According to the algorithms used in predicting the price of cryptocurrencies, articles can be divided into two categories [8], i.e., i) use of basic learning models such as support vector machines, decision trees, and shallow neural networks; and ii) use of deep learning models, reinforcement learning, or hybrid models (combining several deep learning methods). Also, during the review of previous articles [4], [9], the authors have found another classification that divides the papers into the following three categories according to the type of data used in predicting cryptocurrencies, i.e., i) use price data; ii) use price data along with social media and news data; and iii) use price data with technical analysis data, fundamental data, or blockchain data.…”

Section: Social Network and Sentiment Analysismentioning

confidence: 99%

See 1 more Smart Citation

Cryptocurrencies investment framework using sentiment analysis of Twitter influencers

Chahooki

Jahanbin

Sutikno

2023

IJEECS

View full text Add to dashboard Cite

<span>In recent years, cryptocurrency technology has become an attractive area for investment due to its transparency, independence, and non-transactional nature. Many analysts and researchers talk daily on social media about the future of various cryptocurrencies. These ideas can significantly impact whether or not people are willing to invest. This paper provides a framework to help traders learn about the opinions of influential people and organizations in the field. Over the course of six months, the sentiment of more than 90 significant Twitter users was extracted for the proposed framework. In this study, we used the Vader open-source tool for sentiment analysis. This paper provides an excellent opportunity for investment through sentiment analysis<em> </em>of lesser-known or emerging cryptocurrencies. Also in this paper, we introduce the user importance factor to calculate the value of each tweet based on the number of retweets and comments. This factor shows the importance of their opinions instead of considering the number of followers of the authors. This factor causes a lower coefficient to be assigned to an author's opinion if it decreases in importance over time. The results show that in the short and long term, users' opinions are very effective in the market for cryptocurrencies and in predicting its price </span> trend.

show abstract

Section: Social Network and Sentiment Analysismentioning

confidence: 99%

“…The results show GRU performed better at predicting all three cryptocurrencies than LSTM and bi-LSTM models. In [8], a hybrid model of GRU and LSTM for Monroe and Litecoin prediction is presented.…”

Section: Use Of Price Datamentioning

confidence: 99%

Cryptocurrencies investment framework using sentiment analysis of Twitter influencers

Chahooki

Jahanbin

Sutikno

2023

IJEECS

View full text Add to dashboard Cite

show abstract

“…The model realizes feedforward, LSTM, and GRU, artificial neural network technology based on tree and random forest, and finally believes that RNN and GBC models are most suitable for forecasting the short-term bitcoin market. Biswas et al proposed a new method to predict the value of a digital currency based on the LSTM model by considering several variables, such as stock market value, quantity, distribution, and high-end delivery [6]. The actual prediction results are effective.…”

Section: Research On the Price Forecast Of Digital Currencymentioning

confidence: 99%

Research on Price Prediction of Digital Currency Based on Machine Learning

Liu

2023

AEMPS

View full text Add to dashboard Cite

Since the invention of digital currency, the social recognition and demand for special currency and similar cryptocurrencies have increased significantly with the development of digital currency and blockchain technology. The rapid rise in the price of digital currency and its significant volatility attracts a large number of users to invest in it as a digital asset. Before the formation of a regulatory strategy with a standardized system, the development of digital currency will undoubtedly have an increasing impact on society, and its price fluctuation will become an unstable factor in society by increasing the risk to users. Therefore, finding out the factors that affect the price of digital currency and forecasting its price has become the focus of research on Bitcoin in recent years. This will not only help investors and relevant institutions understand Bitcoin and the digital currency market but also help improve the financial market and its policies. In this paper, I use a machine learning model to predict the price of digital currency from both numerical and trend aspects. The main contents include the following elements.First, in terms of data characteristics, I comprehensively summarized and referred to the previous research on the price of special currency at home and abroad. Second, in terms of model prediction, I designed a two-stage feature processing method, used three kinds of recurrent neural network models to compare and predict the price of digital currency, and used recursive feature elimination (RFE) and logical regression (LR), random forest (RF), linear discriminant analysis (LDA) Support Vector Machine (SVM) and Naive Bayes (NB), five commonly used machine learning models, are combined to predict the price trend of Bitcoin.

show abstract

“…In addition to only using price data, other exogenous factors that directly and indirectly influence cryptocurrency prices have also been utilized for prediction. Biswas et al use an LSTM-based prediction model that uses exogenous factors, including stock market capitalization, volume, distribution, and high-end delivery, to predict BTC prices [35]. Bai et al suggest using other cryptocurrencies' price data to classify BTC price movement [36].…”

Section: Cryptocurrency Price Predictionmentioning

confidence: 99%

A Deep Learning-Based Cryptocurrency Price Prediction Model That Uses On-Chain Data

et al. 2022

View full text Add to dashboard Cite

Cryptocurrency has recently attracted substantial interest from investors due to its underlying philosophy of decentralization and transparency. Considering cryptocurrency's volatility and unique characteristics, accurate price prediction is essential for developing successful investment strategies. To this end, the authors of this work propose a novel framework that predicts the price of Bitcoin (BTC), a dominant cryptocurrency. For stable prediction performance in unseen price range, the change point detection technique is employed. In particular, it is used to segment time-series data so that normalization can be separately conducted based on segmentation. In addition, on-chain data, the unique records listed on the blockchain that are inherent in cryptocurrencies, are collected and utilized as input variables to predict prices. Furthermore, this work proposes self-attention-based multiple long short-term memory (SAM-LSTM), which consists of multiple LSTM modules for on-chain variable groups and the attention mechanism, for the prediction model. Experiments with real-world BTC price data and various method setups have proven the proposed framework's effectiveness in BTC price prediction. The results are promising, with the highest MAE, RMSE, MSE, and MAPE values of 0.3462, 0.5035, 0.2536, and 1.3251, respectively.

show abstract

Cryptocurrency Price Prediction Using Neural Networks and Deep Learning

Cited by 18 publications

References 13 publications

Cryptocurrencies investment framework using sentiment analysis of Twitter influencers

Cryptocurrencies investment framework using sentiment analysis of Twitter influencers

Research on Price Prediction of Digital Currency Based on Machine Learning

A Deep Learning-Based Cryptocurrency Price Prediction Model That Uses On-Chain Data

Contact Info

Product

Resources

About