A Decision Support System for Municipal Budget Plan Decisions - New Contributions in Information Systems and Technologies - page 120

A Decision Support System for Municipal
Budget Plan Decisions

Hugo Rego 1 , Armando B. Mendes 2,4 , and Hélia Guerra 3,4

1 Câmara Municipal da Lagoa, Açores, 9560-045 Lagoa, Portugal
2 CEEAplA, Universidade dos Açores, 9500-801 Ponta Delgada, Portugal
3 ALGORITMI, Universidade do Minho, 4800-058 Guimarães, Portugal
4 Depart. de Matemática, Universidade dos Açores, 9500-801 Ponta Delgada, Portugal
[e-mail], {amendes,helia}@uac.pt

Abstract. This paper describes a Decision Support System to provide indicators
to support budget plan decisions, in a local government organization, the
municipality of Lagoa - S. Miguel, Azores. The work includes system
modeling, using the UML notation, the development of a MySQL relational
database, algorithms for data collection using PHP, and forecasting models
using R functions, such as exponential smoothing, classical decomposition with
linear trend, and ARIMA models. Users have access to predictions made by
different models for several indicators, being suggested to use the models with
closest to zero errors. From the analysis performed considering 12 years data, it
is concluded that for most of indicators, the classical decomposition model is
the most successful. However, for some indicators, it was found that the two
error measures used are not consistent. In these cases, the final decision is left
to the decision-maker, taking advantage of his domain knowledge.

Keywords: DSS, UML, economic indicators, R, prediction models.

1 Introduction

In an organization, management decisions are based on guidelines supplied by its
areas of expertise. Given the current economic conditions, the number of local
authorities, such as municipalities, giving importance to a rigorous, careful, and
financial management are increasing. Management decisions are required for
preparing the Budget Plan, according to economic assumptions and a financial and
political conjuncture. These decisions will satisfy the needs of the municipality and its
citizens in various areas of expertise such as social, housing, spatial planning,
sanitation, water supply, solid waste, environment protection and conservation,
culture, sports, among others. Since these needs require better information from the
municipal management system, the decision support system (DSS) described in this
paper intends to complement the existing system with a collection and aggregation of
indicators and introducing predictive models.
A decision support system [1], in general, consists of four elements: a language system,
a presentation system, a knowledge management system and a problem-processing