Question 1a

Decomposition Analysis

The trend component indicates the nature of currency in circulation within the observed period in
relation to economic growth or alteration of monetary base. Seasonal decomposition aims at revealing
notable variations in values and shows that they rise notably in December and January, which might be
associated with higher consumer activity during festive months. The last part involves short-term
fluctuations in the data that remain after trend and seasonal adjustments have been made; random
components. Besides, this improves the understanding of currency distribution further while creating a
solid foundation for accurate forecasting models, which can be used to predict the trends in the future.

Question 1b
We note of a slight decrease from the understanding when forecasted that is towards the end of the
year but in the beginning we note that the currency is of high value this might be due to the changes
experienced during these times and the economic factors more so we note of an increase maybe as an
assumption could be attributed to Covid era during the time making the currency much more favored.

Question 1c

Model Name RMSE

Seasonal Naive 31443.44
Exponential Smoothing 19150.39
ARIMA 30843.97

As for the performance, the Exponential Smoothing Model yielded the best results with an RMSE of
19150. Such a value of Pe is equal to 39, which reflects the model’s ability to track changes in values of
actual currency in circulation and reflect tendencies and fluctuations of both short- and long-term
timescales in the dataset. In contrast, the estimated RMSE from the employed Seasonal Naive Model
amounts to 31443. 44, showed the overall poor performance due to its use of corresponding month of
the preceding year that cannot effectively respond to overall change of trends or seasonal variation of
flows. The ARIMA Model for our dataset is, with the RMSE of 30843. 97 showed a slightly better result
than the Naive Model, but lower than the Exponential Smoothing Model. This means that although
there are some complicated patterns that the ARIMA models are capable of identifying, these models
may have to be constantly modified in order to better capture and forecast data that might have a
seasonality aspect to it such as this one for currency circulation.

Question 2a

Basic Loan Rate of the Bank of Japan is thought to be an important pointer towards the monetary policy
course adopted by the country’s central bank in a bid to promote economic growth, manage inflation
and support the domestic financial sector. A change in this rate also affects exchange rates because it
entice foreign investments to Japan when the rates are higher, JPY might be stronger than USD, for
example. Also, these rates are watched keenly in the financial markets as traders and investors expect
future changes of the rates to influence the JPY/USD exchange rates, which also affects the market
mood and movement.

Question 2b

AR-X - GARCH Model Results

==============================================================================

Dep. Variable: Log_Return R-squared: -0.001

Mean Model: AR-X Adj. R-squared: -0.001

Vol Model: GARCH Log-Likelihood: -6989.36

Distribution: Normal AIC: 13990.7

Method: Maximum Likelihood BIC: 14025.9

No. Observations: 2605

Date: Sun, Jul 14 2024 Df Residuals: 2602

Time: 21:26:48 Df Model: 3

Mean Model

================================================================================

coef std err t P>|t| 95.0% Conf. Int.

--------------------------------------------------------------------------------

Const 0.1419 6.217e-02 2.282 2.247e-02 [2.004e-02, 0.264]

Log_Return[1] 0.0148 2.197e-02 0.676 0.499 [-2.820e-02,5.790e-02]

Rate 0.0425 2.654e-02 1.601 0.109 [-9.520e-03,9.453e-02]

 Volatility Model

==========================================================================

coef std err t P>|t| 95.0% Conf. Int.

--------------------------------------------------------------------------

omega 0.3066 0.132 2.317 2.049e-02 [4.728e-02, 0.566]

alpha[1] 0.0828 2.164e-02 3.826 1.302e-04 [4.039e-02, 0.125]

beta[1] 0.8995 2.595e-02 34.658 3.420e-263 [ 0.849, 0.950]

==========================================================================

Covariance estimator: robust

The convergence of the AR-X - GARCH model is successful according to the terminal message:
”Optimization terminated successfully. ” The obtained log-likelihood figure of around -6989. It might be
a bit high but 36 indicates a good fit of the model to the data. Based on the estimate result of the mean
model (AR-X), the constant term is 0. 1419, and the standard error is equal to 0. 06217, which is more
than 0. The coefficient for lagged log returns is 0. 0148 with the standard error of 0. 02197, and hence it
is statistically insignificant with a p-value of 0. 499; however, it shows a positive sign which suggests that
there is a slight positive relationship between the two series. The coefficient for Basic Loan Rate an
exogenous variable is 0. Slightly significant statistical result was obtained with a mean value of 0425
(standard error 0. 02654) with marginal significance level of (0. 109). In GARCH, omega which is the
constant term is estimated to be 0. 3066 (standard error of 0. 132) which presented the AAV, testifying
the long-term volatility average. Alpha[1] with the value of 0. 0828 and standard error of 0. 02164 shows
the effect of the squared residuals from the previous period on the current volatility level, whereas
Beta[1] with the value 0. Consequently, these results help in understanding the fluctuations in the mean
and volatilities of the model to continue the analysis and control risk management in various areas of
financial forecasting and decision-making

Question 2c
.

The following general observations can be made with regard to the above graph of standardized
residuals. First, one can distinguish the presence of volatility clustering, which indicates the disposition
of incidents of high volatility and other interval with low volatility. This is seen by having large positive
and negative residuals all bunched up together in sets. Secondly, although the residuals seem to
oscillate random around zero with no permanent up-trend, suggesting that the overall picture of trade is
well-caught by the model alternation, cluster of large residuals points to a possibility that some
dynamics are neglected completely. Thirdly, the comparison with the selected critical VaR levels which is
located at the top of the 10% level portrayed by the green colored dotted line and the lower part of the
figure by the red colored dotted line indicate that the standardized residuals are beyond these levels
especially in the lower side. This fact means that the model might underestimate the probabilities of
negative, rather extreme events, as the exceedance in question is rather frequent. In comparison with
the identified patterns of the residual, there are certain signs that the model in question could be more
suitable to capture the marked increases in residual and extreme events.