BDI & SCFI prediction (‘22/21W)

In the 21st week, BDI and SCFI predicted values and actual values are compared and tested.

---

1.     Last Week’s forecasts

1-1.        BDI, Actual Vs. Predicted

Date	Last week Forecast	Actual BDI	MAPE(%)	Accuracy(%)
‘22/20W(5/16~20)	3,203.596	3,200.40	0.1%	99.9%

 

1-2.        SCFI, Actual Vs. Predicted

Date	Last week Forecast	Actual SCFI	MAPE(%)	Accuracy(%)
‘22/20W(5/16~20)	4,137.046	4,162.69	0.6%	99.4%

 The prediction accuracy of BDI and SCFI was 99.9% and 99.4%, respectively. The predicted value (3,203.596) and actual value (3,200.40) of BDI, and predicted value (4,137.046) and actual value (4,162.69) of SCFI all achieved high accuracy. The singularity is that the SCFI has finally rebounded after 18 weeks. Although this study predicted a slight decline in the 20th week, the actual SCFI value changed to a slight increase, so it is necessary to pay attention to the future movement. The average BDI MAPE value for the last 8 predictions is 3.9% and the prediction rate is 96.1%, and the SCFI average MAPE value is 0.7% and the prediction rate is 99.3%.

---

2.     BDI forecast

2-1. ARIMA, Time series analysis

 For the BDI forecast, I used weekly data (433 pieces) from January 3, 2014 to May 20, 2022 to predict the freight for three weeks in the future.

Date	Forecast	Trend(WoW)
‘22/21W(5/23~27)	3,185.337	↘
‘22/22W(5/30~6.3)	3,121.851	↘
‘22/23W(6/6~10)	3,014.918	↓

 As shown in the table and figure above, the BDI (as of 5/20: 3,200.40) rose 6.4% from the previous week (as of 5/13: 3,008.60) and reached a new high in 2022. If you look at the weekly average value, it is the highest level in 22 weeks since December 10, 21st. As a result of the ARIMA model, it is predicted that there will be a slight decline over the next three weeks.

Ref) BDI & SCFI prediction (‘22/20W) (tistory.com)

BDI & SCFI prediction (‘22/20W)

 

2-2. Logistic regression analysis

 Logistic regression analysis was performed with the same data predicted by the ARIMA model previously.

 The expected trend for next week was 0.897, which was higher than the baseline 0.5. While the previous ARIMA model predicted a slight decline in BDI at 22 weeks, logistic regression predicted a high rise in BDI even at week 22, so the advantages and disadvantages of the two models can be compared with the results.

---

 

3.     SCFI Outlook

3-1. ARIMA, Time series analysis

 For the SCFI forecast, I used weekly data (631 pieces) from October 16, 2009 to May 20, 2022 to predict the future freight for three weeks.

Date	Forecast	Trend(WoW)
‘22/21W(5/23~27)	4,159.141	→
‘22/22W(5/30~6.3)	4,156.697	→
‘22/23W(6/6~10)	4,147.888	↘

 As shown in the table and figure above, the SCFI (as of 5/20: 4,162.69) succeeded in rebounding for the first time in 18 weeks after falling after the 1/7 SCFI of 5,109.60. Qualitative research analysis shows that there are many factors that increase freight rates, but in light of the fact that the 5/20 rebound was not large in econometric analysis, it is expected that freight rates will remain flat for the next three weeks.

 

3-2. Logistic regression analysis

 

 The results of the logistic regression analysis model of SCFI are also the same as the ARIMA values. With the predicted value of 0.385, the next week's SCFI freight direction was predicted to be down.

 

3-3. SVR model

Ref) SCFI Prediction Using SVR Model (tistory.com)

SCFI Prediction Using SVR Model

 For the SCFI index forecast, I used weekly data (72 pieces) from January 01, 2021 to May 20, 2022 to predict the future freight for three weeks. Like the previous model, the SVM model also predicted a continuous decline in freight rates. However, if SCFI rates continue to rise in the coming 21 weeks, the major direction of freight rates may change to an upward trend.

 

Date	Forecast	Trend(WoW)
‘22/21W(5/23~27)	4,017.463	↘
‘22/22W(5/30~6.3)	3,993.323	↘
‘22/23W(6/6~10)	3,969.667	→

 

 The direction of SCFI rates is (Fall: global economic downturn due to US interest rate hike) Vs. (Rising: After effective control of the supply of ships based on blank sailing by each shipping company, freight rates rise due to the increase in cargo volume after the Chinese corona lockdown is lifted)

 

Thanks.