Leveraging Time Series Categorization and Temporal Fusion Transformers to Improve Cryptocurrency Price Forecasting
This work addresses the challenge of accurate price prediction for cryptocurrency portfolio management, but it is incremental as it builds on existing methods like Temporal Fusion Transformers with data augmentation.
The paper tackles cryptocurrency price forecasting by categorizing time series into similar subseries and training separate attention-based models for each category, then augmenting training data with other cryptocurrencies to address limited data, achieving improved prediction accuracy.
Organizing and managing cryptocurrency portfolios and decision-making on transactions is crucial in this market. Optimal selection of assets is one of the main challenges that requires accurate prediction of the price of cryptocurrencies. In this work, we categorize the financial time series into several similar subseries to increase prediction accuracy by learning each subseries category with similar behavior. For each category of the subseries, we create a deep learning model based on the attention mechanism to predict the next step of each subseries. Due to the limited amount of cryptocurrency data for training models, if the number of categories increases, the amount of training data for each model will decrease, and some complex models will not be trained well due to the large number of parameters. To overcome this challenge, we propose to combine the time series data of other cryptocurrencies to increase the amount of data for each category, hence increasing the accuracy of the models corresponding to each category.