Leveraging Time Series Categorization and Temporal Fusion Transformers to Improve Cryptocurrency Price Forecasting

TL;DR

This paper introduces a method that categorizes cryptocurrency time series and uses Temporal Fusion Transformers to improve price prediction accuracy by leveraging data sharing among similar categories.

Contribution

It proposes a novel approach combining time series categorization with data augmentation across cryptocurrencies to enhance deep learning model training and prediction accuracy.

Findings

Categorizing time series improves prediction accuracy.

Data augmentation across cryptocurrencies enhances model training.

Attention-based models effectively predict cryptocurrency prices.

Abstract

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.