Causal Feature Engineering of Price Directions of Cryptocurrencies using Dynamic Bayesian Networks
- URL: http://arxiv.org/abs/2306.08157v2
- Date: Mon, 29 Apr 2024 00:56:29 GMT
- Title: Causal Feature Engineering of Price Directions of Cryptocurrencies using Dynamic Bayesian Networks
- Authors: Rasoul Amirzadeh, Asef Nazari, Dhananjay Thiruvady, Mong Shan Ee,
- Abstract summary: Despite their growing popularity, cryptocurrencies remain a high-risk investment due to their price volatility and uncertainty.
This paper proposes a dynamic Bayesian network (DBN) approach, which can predict the price direction of five popular.
other than Bitcoin in the next trading day.
- Score: 1.4356611205757077
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Cryptocurrencies have gained popularity across various sectors, especially in finance and investment. The popularity is partly due to their unique specifications originating from blockchain-related characteristics such as privacy, decentralisation, and untraceability. Despite their growing popularity, cryptocurrencies remain a high-risk investment due to their price volatility and uncertainty. The inherent volatility in cryptocurrency prices, coupled with internal cryptocurrency-related factors and external influential global economic factors makes predicting their prices and price movement directions challenging. Nevertheless, the knowledge obtained from predicting the direction of cryptocurrency prices can provide valuable guidance for investors in making informed investment decisions. To address this issue, this paper proposes a dynamic Bayesian network (DBN) approach, which can model complex systems in multivariate settings, to predict the price movement direction of five popular altcoins (cryptocurrencies other than Bitcoin) in the next trading day. The efficacy of the proposed model in predicting cryptocurrency price directions is evaluated from two perspectives. Firstly, our proposed approach is compared to two baseline models, namely an auto-regressive integrated moving average and support vector regression. Secondly, from a feature engineering point of view, the impact of twenty-three different features, grouped into four categories, on the DBN's prediction performance is investigated. The experimental results demonstrate that the DBN significantly outperforms the baseline models. In addition, among the groups of features, technical indicators are found to be the most effective predictors of cryptocurrency price directions.
Related papers
- Cryptocurrency Price Forecasting Using XGBoost Regressor and Technical Indicators [2.038893829552158]
This study introduces a machine learning approach to predict cryptocurrency prices.
We make use of important technical indicators such as Exponential Moving Average (EMA) and Moving Average Convergence Divergence (MACD) to train and feed the XGBoost regressor model.
We evaluate the model's performance through various simulations, showing promising results.
arXiv Detail & Related papers (2024-07-16T14:41:27Z) - DAM: A Universal Dual Attention Mechanism for Multimodal Timeseries Cryptocurrency Trend Forecasting [3.8965079384103865]
This paper presents a novel Dual Attention Mechanism (DAM) for forecasting cryptocurrency trends using multimodal time-series data.
Our approach integrates critical cryptocurrency metrics with sentiment data from news and social media analyzed through CryptoBERT.
By combining elements of distributed systems, natural language processing, and financial forecasting, our method outperforms conventional models like LSTM and Transformer by up to 20% in prediction accuracy.
arXiv Detail & Related papers (2024-05-01T13:58:01Z) - Forecasting Cryptocurrency Prices Using Deep Learning: Integrating
Financial, Blockchain, and Text Data [3.8443430569753025]
We analyse the influence of public sentiment on cryptocurrency valuations using advanced deep learning NLP methods.
We compare the performance of various ML models, both with and without NLP data integration.
We discover that pre-trained models, such as Twitter-RoBERTa and BART MNLI, are highly effective in capturing market sentiment.
arXiv Detail & Related papers (2023-11-23T16:14:44Z) - Cryptocurrency Portfolio Optimization by Neural Networks [81.20955733184398]
This paper proposes an effective algorithm based on neural networks to take advantage of these investment products.
A deep neural network, which outputs the allocation weight of each asset at a time interval, is trained to maximize the Sharpe ratio.
A novel loss term is proposed to regulate the network's bias towards a specific asset, thus enforcing the network to learn an allocation strategy that is close to a minimum variance strategy.
arXiv Detail & Related papers (2023-10-02T12:33:28Z) - Diffusion Variational Autoencoder for Tackling Stochasticity in
Multi-Step Regression Stock Price Prediction [54.21695754082441]
Multi-step stock price prediction over a long-term horizon is crucial for forecasting its volatility.
Current solutions to multi-step stock price prediction are mostly designed for single-step, classification-based predictions.
We combine a deep hierarchical variational-autoencoder (VAE) and diffusion probabilistic techniques to do seq2seq stock prediction.
Our model is shown to outperform state-of-the-art solutions in terms of its prediction accuracy and variance.
arXiv Detail & Related papers (2023-08-18T16:21:15Z) - Can ChatGPT Forecast Stock Price Movements? Return Predictability and
Large Language Models [57.70351255180495]
We use ChatGPT to assess whether each headline is good, bad, or neutral for firms' stock prices.
We find that ChatGPT outperforms traditional sentiment analysis methods.
Long-short strategies based on ChatGPT-4 deliver the highest Sharpe ratio.
arXiv Detail & Related papers (2023-04-15T19:22:37Z) - Modelling Determinants of Cryptocurrency Prices: A Bayesian Network
Approach [0.8602553195689513]
Social media is the most significant influencing factor of the prices of cryptocurrencies.
It is not possible to generalise the coins' reactions against the changes in the factors.
The coins need to be studied separately for a particular price movement investigation.
arXiv Detail & Related papers (2023-03-26T21:54:41Z) - Factor Investing with a Deep Multi-Factor Model [123.52358449455231]
We develop a novel deep multi-factor model that adopts industry neutralization and market neutralization modules with clear financial insights.
Tests on real-world stock market data demonstrate the effectiveness of our deep multi-factor model.
arXiv Detail & Related papers (2022-10-22T14:47:11Z) - Ensemble and Multimodal Approach for Forecasting Cryptocurrency Price [5.333582981327497]
Forecasting the crypto-fiat currency exchange rate is an extremely challenging task.
This paper proposes a multimodal AdaBoost-LSTM ensemble approach that employs all modalities which derive price fluctuation.
Tests demonstrate the outperformance of the proposed approach compared to existing tools and methods with a 19.29% improvement.
arXiv Detail & Related papers (2022-02-12T21:39:29Z) - A Sentiment Analysis Approach to the Prediction of Market Volatility [62.997667081978825]
We have explored the relationship between sentiment extracted from financial news and tweets and FTSE100 movements.
The sentiment captured from news headlines could be used as a signal to predict market returns; the same does not apply for volatility.
We developed an accurate classifier for the prediction of market volatility in response to the arrival of new information.
arXiv Detail & Related papers (2020-12-10T01:15:48Z) - Reinforcement-Learning based Portfolio Management with Augmented Asset
Movement Prediction States [71.54651874063865]
Portfolio management (PM) aims to achieve investment goals such as maximal profits or minimal risks.
In this paper, we propose SARL, a novel State-Augmented RL framework for PM.
Our framework aims to address two unique challenges in financial PM: (1) data Heterogeneous data -- the collected information for each asset is usually diverse, noisy and imbalanced (e.g., news articles); and (2) environment uncertainty -- the financial market is versatile and non-stationary.
arXiv Detail & Related papers (2020-02-09T08:10:03Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.