INTRODUCTION:

1. Rationale:
1.1. Industry:
Since the political stability and the acceleration of urbanization and industrialization,
Vietnam has been offering spacious and attractive opportunities for many foreign
companies wishing to invest and export their products. In fact, according to the records
from logistics companies, the trend of import and export as well as the demand for
international shipments of goods are constantly increasing each year, which contributes
directly to Vietnam annual GDP growth. In order to facilitate the trend, Vietnam should
focus on helping businesses reduce the costs associated with transporting goods across
borders. In fact, logistics costs of Vietnam are accounted for an average of about 21% of
product prices, relatively high compared to developed countries in the world. Besides, the
scale of the current logistics service sector accounts for only 3 ~ 4% of GDP with a potential
of growth of about 15 ~ 20% / year, which is expected to contribute 8 ~ 10% of GDP by
2025 (according to VLA). The absence of enterprises operating in this sector and poorly
developed transport facilities are the underlying causes of the reduction of the import and
export dynamics of domestic and foreign enterprises.
In fact, to reduce investment pressure and shorten the process of infrastructure
development, Vietnam seaport system, which annually receives 90% of total imports and
exports and is the focal point for transforming mode of transport from sea to rail, road and
inland waterway transport, should be set on a prioritized focus. Up to now, Vietnam has
had 44 seaport areas and 263 seaports with a total length of about 89 km and the capacity
of 550 - 570 million tons/year. In particular, deep-water seaports, gateway ports together
with international transshipment ports, which can provide loading and unloading services
for ships of 100-200 thousand tons, have been invested in construction in both the North
and the South. However, on encouraging the flow of goods across borders and reaching the
national economic development goal, there is still a need for paying more attention to
businesses operating in logistics and port operations, especially domestic large enterprises,
in order for Vietnam to timely provide and supplement regulations and necessary legal
frameworks.
1.2. Company:
Gemadept Corporation (GMD) was established in 1990 and was among the first 3
companies being selected by the government for equitization in 1993. From 2002,
Gemadept was officially listed on Vietnam Stock Exchange. Gemadept is now owning and
operating a large port system from North to South, in big cities and key economic zones,
towards the project of operating Gemalink deep-water port (Cai Mep - Thi Vai) in 2020,
capable of receiving 200,000 ton vessels download. After almost 30 years of establishment
and development, Gemadept is the pioneer in many sectors, especially one of the leading
enterprises in its core businesses including Port operation and Logistics in Vietnam market.
With scores of subsidiaties and affiliates, business network stretching in many big cities
 and provinces of Vietnam, at major industrial zones and reaching out to other countries in
ASEAN, Gemadept has been ranked among Vietnam’s Top 500 largest enterprises, Top
1000 enterprises having the largest contribution of corporate income tax to national budget,
Top 20 Logistics Enterprises in Vietnam, Top 50 Vietnamese Best Performing Companies,
Top 50 Best Vietnamese Listed Companies by Forbes, etc. for many consecutive years. In
2020, the company aims to become the leading logistics service provider in Indochina and
the leading in OOG Cargo Transport.
2. Objectives:
Although the company also has a relatively stable revenue growth rate over the years
(2002-2017), it is still affected by fluctuations in the world maritime market and the
changes in the business of large shipping lines in general. The occupation of a large
domestic market share also shows high representativeness and feasibility for a true
prediction. The revenue analysis of Gemadept, therefore, can truly reflect the general
situation of the port operation industry in Vietnam over years or after certain events. At the
same time, policymakers can base on it to make suitable regulations for development and
competition and investors can make right decision with GMD stock.
2.1. Insider:
- Finding out the level of revenue dependence on trend and seasonal components in the
past in order to plan the best preparation (optimize costs and maximize profits) for
businesses.
- Forecasting the trend of demand for the services, thereby finding out insights affecting
customer needs and proposing related solutions to adapt or change that demand
following the business plan.
- Using difference between forecasting and reality when erratic events occurred in the
past to predict the impact of future similar events.
- Testing different forecasting models and comparing results to build the most suitable
model with the highest accuracy to apply in the future.
2.2. Outsider:
- Estimating revenue trend from timeline data will help investors find the right time to
buy or sell GMD shares: Will the stocks continue to profit in the next 1-3 quarters?
When investors should consider to stop investing in that stock?
- Investigating the occurence and frequency of irregular factors on revenue in the past to
predict the impact level of risk in future investment. The higher the level is, the greater
the risk.
3. Previous related researches:
- There is a wide range of researches on prediction about the revenue, development,
sales,... in the economy in general and logistic industry in particular.
- In today’s competitive environment, predicting sales for upcoming periods at right
quantity is very crucial for ensuring product availability as well as improving customer
satisfaction. Therefore, in 2017, C. L. Karmaker, P. K. Halder,and E. Sarker had a
Study of Time Series Model for Predicting Jute Yarn Demand. The main goal of their
study is to determine the most appropriate forecasting technique for upcoming sale of
jute yarn for jute products manufacturing industry in Bangladesh. Necessary sales data
 of jute yarn were collected from a jute product manufacturer industry in Bangladesh,
namely, Akij Jute Mills, Akij Group Ltd., in Noapara, Jessore. Different time series
analysis is performed on 208-week demand data using Minitab 17 package and
measures of accuracy are calculated . To make their research more accurate, they even
used eight different forecasting techniques including simple moving average, single
exponential smoothing, trend analysis, Winters method, and Holt’s method were
performed by statistical technique using Minitab 17 software. Performance of eight
forecasting methods is evaluated and results show that the suitable method is Winters
additive model to forecast their actual demand. That study help the industry as well as
others Bangladeshi manufacturers to reduce the deviation between actual and
forecasted demand through the selection of the contingent forecasting method. (1)
- Jie Zhu, Hong Zhang, Li Zhou ( 2015) did a Research on Logistics Demand Forecasting
and Transportation Structure of Beijing Based on Grey Prediction Model. They
analyzed the present situation of Beijing logistics development, starting from the total
economic output, economic structure, economic location and other aspects, basic
economic situation of Beijing is analyzed. They used the econometric model to analyze
and forecast the total demand analysis of Beijing logistics, also discussed the
influencing factors of Beijing logistics demand. Finally , they reached to the conclusion
that Beijing logistics demand presents the fast growth in the future five years. (2)
- In 2016, 3 people from the Faculty of Economics in Osijek, University of Josip Juraj
Strossmayer in Osijek did a study predicting company growth using logistic regression
and neural networks. Their paper aims to establish an efficient model for predicting
company growth by leveraging the strengths of logistic regression and neural networks.
According to them, besides innovation and venture creation, predicting company
growth is one of the most important aspects of entrepreneurship research. In economic
theory and practice, growth can be measured in many ways, such as in terms of revenue
generation (sales), employment and asset growth, but also in terms of product quality
and market position . In their paper, the asset growth is a measure of company growth
and is used to explore the various financial determinants important in predicting asset
growth. In addition, measuring a company growth in terms of sales, number of
employees or productivity is certainly a noteworthy test. The research they did may
assist investors and economic policy makers in providing them with tools for
classifying companies as having growth potential, especially those small and medium
enterprises. (3)
1. C. L. Karmaker, P. K. Halder, and E. Sarker : A Study of Time Series Model for
Predicting Jute Yarn Demand: Case Study, Journal of Industrial Engineering,
Volume 2017, Article ID 2061260
2. Jie Zhu, Hong Zhang, Li Zhou, School of Information, Beijing Wuzi University,
Beijing, China: Research on Beijing Total Logistics Demand Prediction Based
on Grey Prediction Model, American Journal of Theoretical and Applied Statistics,
Volume 4, Issue 3, May 2015.
3. Marijana Zekić-Sušac , Nataša Šarlija , Adela Has and Ana Bilandžić, Faculty of
Economics in Osijek, University of Josip Juraj Strossmayer in Osijek : Predicting
company growth using logistic regression and neural networks

DATA COLLECTION:
The secondary data was collected from Vietstock.vn for Gemadept (GMD)'s quarterly revenue
from Q3, 2004 to Q2, 2017 (n=52 quarters) in order to analyze and identify appropriate models
for the company's revenue growth trend. The selection of sources to collect data is determined
based on the following factors:
- Suitability
Vietstock.vn is a specialized website providing statistics of listed companies including
quarterly or annual financial statements, corporate news related to securities and
finance, etc. Accordingly, the collection of quarterly revenue data will allow to
determine the effect of revenue by seasonal components.
- Availability and Convenience
Since a complete and accurate database was built from the early days of establishment
of Vietnam stock market, it would be convenient to search, compare and download data
from the website. Besides, a large enough sample size can also be accessed to produce
a more accurate statistics model.
- Reliability
Data aggregation of Vietstock.vn is based on reliable sources such as: State Bank,
General Statistics Office, Foreign Investment Department - Ministry of Planning &
Investment, State Securities Commission, Department of Communications Securities
Trading Center, Hanoi Stock Exchange, Vietnam Industrial and Commercial Bank
(VietinBank), Asian Development Bank (ADB), The Wall Street Journal, etc.