Temporal Analysis of Blockchain Transactions in the Metaverse Using Time Series

This study aims to analyze the temporal data of blockchain transactions in the metaverse using time series analysis techniques such as ARIMA and LSTM. The primary focus of this research is to identify significant trends and time patterns in transaction activities within the metaverse. By employing ARIMA, the time series data is decomposed into trend, seasonal, and residual components, providing crucial insights into its structure. The ARIMA model demonstrated a mean absolute error (MAE) of 10,525.73, a mean squared error (MSE) of 150,247,506.45, and a root mean squared error (RMSE) of 12,259.65, indicating a reasonably good fit with some potential for improvement. To capture more complex temporal dependencies in the data, an LSTM model was also applied. The performance of the LSTM model, evaluated using RMSE, was 10.0 for the training set and 15.0 for the testing set. The higher RMSE on the testing set indicates slight overfitting, where the model fits the training data better than unseen data. However, the LSTM model showed strong capability in predicting daily transaction values with fairly high accuracy, despite some minor discrepancies between actual and predicted values. Descriptive statistical analysis of the transaction data revealed that the average daily transaction volume was 108,225.72 with a standard deviation of 8,489.47, indicating significant variability. The daily transaction range spanned from 83,052.86 to 134,869.80, reflecting a wide variation in transaction volume. The results of this study highlight the importance of temporal analysis in understanding blockchain transactions in the metaverse. Insights gained from this analysis can assist in strategic planning and decision-making within the metaverse ecosystem. By further refining model tuning and employing more advanced analysis techniques, predictive accuracy can be enhanced, providing more comprehensive insights and more accurate predictions of transaction behavior.