Abstract—In the field of business management many prediction problems such as prediction of market demand, product prices, project cost flow, product quality, etc., are very complex, uncertain, dynamic, mutable, and usually they are not adequately modeled by statistical or classical mathematical methods based on crisp sets and traditional logic. This paper shows benefits that could be achieved by applying a model based on Artificial Neural Network (ANN) for solving certain type of prediction problems, because it can better deal with uncertainty, partial truth, incomplete data and complexity. A model based on ANN for solving prediction problems is first defined and explained. A case study for price estimation of the apartments in the city Budva, Montenegro, is considered and the results are discussed. The main factors influencing the apartment prices are established and analyzed. The benefits of the ANN model are pointed out.
[1]
Soundar Kumara,et al.
Neuroform—Neural Network System for Vertical Formwork Selection
,
1992
.
[2]
Esther Levin,et al.
A statistical approach to learning and generalization in layered neural networks
,
1989,
Proc. IEEE.
[3]
D.R. Hush,et al.
Progress in supervised neural networks
,
1993,
IEEE Signal Processing Magazine.
[4]
A. Halim Boussabaine,et al.
The use of artificial neural networks in construction management: a review
,
1996
.
[5]
Bernard Widrow,et al.
Neural networks: applications in industry, business and science
,
1994,
CACM.
[6]
Teuvo Kohonen,et al.
An introduction to neural computing
,
1988,
Neural Networks.