Less Complexity, More Insight: A Correlation-Based Approach to Price Prediction of USDT/IRT Using USD/IRT

Tether (USDT), a widely used stablecoin pegged to the US dollar, plays a vital role in the digital currency market as a bridge between cryptocurrencies and fiat currencies. In the context of Iran, the USDT/IRT (Tether to Iranian Toman) exchange rate is of particular importance for traders and investors. However, despite its relevance, prior studies have not explored the potential of using correlated indices to simplify and improve the prediction of the USDT/IRT price. This research addresses this gap by first investigating the relationship between USDT/IRT and USD/IRT (Dollar to Iranian Toman), revealing a strong linear correlation between the two indices. Based on this finding, two linear modeling approaches—Linear Regression (LR) and Support Vector Regression (SVR)—were applied to predict USDT/IRT using USD/IRT as the input feature. The comparative results demonstrate that SVR outperformed LR across all evaluation metrics, achieving a lower Root Mean Square Error (RMSE) of 1520 compared to 1554 for LR. This study highlights that leveraging a correlated feature can reduce modeling complexity while maintaining or improving predictive accuracy, offering a viable alternative to more complex nonlinear approaches in specific contexts.