Combined Throughput Prediction of Fujian Coastal Ports based on Grey Model and Markov Chain

The rationality and reliability of port throughput forecasting results directly affect the rational arrangement of port resources, which is of great significance to the formulation of future port development strategy. This paper collects decades of historical data of Fujian coastal ports, combines the Grey model GM (1,1) prediction with Markov chain, uses Markov chain to reflect the randomness of variable fluctuations, corrects the predicted value, and forecasts the port cargo throughput from 2015 to 2016. The results show that the average absolute error of the Grey model modified by Markov process decreases from 5.4% to 0.04%. Through comparison, we can find that the result of Grey Markov chain is more accurate than that of single grey prediction.