Mahidol University Logo
Faculty of ICT, Mahidol University
 

Admissions

Printable Version

 

DESIGNING THE MODEL-BASED SYSTEM FOR THAI TAX REVENUE FORECASTING (MBS-TTRF)

 

TITLE DESIGNING THE MODEL-BASED SYSTEM FOR THAI TAX REVENUE FORECASTING (MBS-TTRF)
AUTHOR PATTAMA TOUNPRASERT
DEGREE MASTER OF SCIENCE PROGRAMME IN COMPUTER SCIENCE
FACULTY FACULTY OF SCIENCE
ADVISOR JARERNSRI L. MITRPANONT
CO-ADVISOR SUKANYA PHONGSUPHAP
 
ABSTRACT
In this research project, we propose the Model-Based System for Thai Tax Revenue Forecasting (MBS-TTRF). This system is developed to increase efficiency of Thai Tax Revenue Forecasting in the Revenue Department (RD) via a web-based application. The architecture of MBS-TTRF is composed of four main components: Database Management System (DBMS), Model Base Management System (MBMS), User Interface, and User/Decision Maker. This MBS-TTRF contains essential models for Tax Revenue Forecasting. These modes can be categorized into five types: Existing Thai Tax Revenue Forecasting (ETTRF) Models, New Improved Thai Tax Revenue Forecasting (NITTRF) Models, Supporting Thai Tax Revenue Forecasting (STTRF) Models, Thai Tax Revenue Forecasting Analysis (TTRFA) Models and Thai Tax Revenue Forecasting Accuracy and Control (TTRFAC) Models. The MBS-TTRF provides Model Navigator, which provides flexibility and convenience to users using them to navigate all models to forecast tax revenue. This system supports the data analytical functions: Sensitivity, What-if and Goal-seeking analysis, which is useful for analyzing results before making a decision. Furthermore, this system also improves the accuracy of Thai Tax Revenue Forecasting by developing NITTRF that uses regression approach. In our experiment, we had measured by using Mean Absolute Percentage Error (MAPE), and found that the NITTRF had lower error than ETTRF, which a user/decision maker could use as alternative models to forecast tax revenue. This proposed system is expected to assist a user/decision maker. It reduces time for Thai Tax Revenue Forecasting operation that depends mainly on human expertise and improves the accuracy of Thai Tax Revenue Forecasting.
KEYWORD MODEL-BASED SYSTEM /TAX REVENUE FORECASTING/ SENSITIVITY/WHAT-IF/GOAL-SEEKING/REGRESSION/MAPE

 

Go to Top

 

ICT Building, Mahidol University, 999 Phuttamonthon 4 Road, Salaya, Nakhonpathom 73170 Tel. +66 02 441-0909 Fax. +66 02 849-6099
Mahidol University Computing Center, The Faculty of ICT, Mahidol University , Rama 6 Road, Rajathevi, Bangkok 10400 Tel. +66 02 354-4333 Fax. +66 02 354-7333