A comparative study between the effectiveness of ARIMA and ARFIMA models in predicting the interest rate and the treasury exchange rate in Iran

Subject Areas : Journal of Investment Knowledge

mohadeseh  razaghi ¹ (PhD. Student in Financial Engineering, Department of Financial Management, Faculty of Management and Economy, Sciences and Research Branch, Islamic Azad University)
hashem  nikomaram ² (Prof., Department of Financial Management, Faculty of Management and Economy, Sciences and Research Branch, Islamic Azad University)
Alireza  Heidarzadeh Hanzaei ³ (Assistant Prof. Dr. , Department of Financial Management, Tehran North Branch, Islamic Azad University, Tehran-Iran)
farhad  ghaffari ⁴ (Associate Prof., Department of Economics, Faculty of Management and Economy, Sciences and Research Branch, Islamic Azad University)
Mahdi  Madanchi Zaj ⁵ (Department of Financial Management, Electronic Campus, Islamic Azad University Tehran, Iran)

Received: 2022-10-31 Accepted : 2022-12-10 Published : 2023-09-23

Keywords: Autoregressive Integrated Moving Average (ARIMA), Autoregressive fractionally integrated moving average (ARFIMA), long-term memory, Interest rate forecasting,

Abstract :

Due to the importance of predicting economic variables, different models have been created to predict the future values of variables. In fact, economic models can be tested by checking the level of forecasting accuracy. The main purpose of this study is prediction of Iran interbank offered rate and Iran treasury exchange rate as interest rates indicators for facilitating interest rate risk management. Two econometric models including ARFIMA and ARIMA have been used for forecasting. Thus, the ARFIMA model considering long-term memory and the ARIMA model without considering long-term memory have been considered. The evaluation of the prediction accuracy of the two models using the monthly Iran interbank offered rates data and also the monthly Iran treasury exchange rates data shows that both the interbank offered rates data and the Islamic treasury bond rates data, ARIMA model has a better performance compared to ARFIMA model in predicting data.

References:

✓ ابونوری، عباسعلی، فرخی، فرداد، شجائیان، سیده فاطمه، مقایسه عملکرد شبکههای عصبی مصنوعی) ANN )
و مدل میانگین متحرک انباشته اتورگرسیو ) ARIMA ( در مدلسازی و پیشبینی کوتاهمدت روند نرخ ارز در
ایران، فصلنامۀ دانش سرمایهگذاری، مرداد 1393 .
✓ اشراقی محسن، غفاری، فرهاد، محمدی، تیمور، پیشبینی بازدهی شاخص صنعت پتروشیمی در بورس اوراق
بهادار تهران با استفاده از مدلهای ARIMA و ARFIMA ، مجله فصلنامه اقتصاد کاربردی، سال ششم، پاییز
و زمستان 1395 .

_||_