摘要：In the Basel III era, measuring, managing, mitigating and forecasting interest rate risk has become significant. In the first study of its kind, this paper develops a principal component analysis-based forecasting of interest rates of different maturities and stress testing approach in a univariate auto-regressive integrated moving average (ARIMA) framework in the context of India. Debating the existence of multiple representations of interest rates in the Indian market, the study broke down all the short-term, as well as long-term interest rates to derive the optimal principal component of unique interest rates. These unique interest rates are further exercised to forecast the future interest rates through the ARIMA model. The rolling average method was applied to the recently created Indian volatility index (VIX) to place the stress points. The model performance was examined over this stress point of building multiple scenario analysis. The study found that ARIMA (2-1-1) forecasting model of interest rates produced a better forecast result, both in the case of in-sample and out-of-sample performances as well as in stress periods. From the forecasting results, the study found that the proportionate gain in yield is higher as the maturity increases. By examining the stress period on the basis of eight quarters (2007: Q4 of 2009: Q3) rolling average on Indian volatility Indices, the survey concluded that the Indian economy will reach a stable situation signalled by less volatile interest rates post the second quarter of 2018.
