Naslov
Bus tickets sales forecasting using neuro-genetic methods

Autori
Gold, Hrvoje ; Kavran, Zvonko ; Štefančić, Gordana

Izvornik
Promet-Traffic-Traffico (0353-5320) 10 (1998), 1-2; 57-68

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
bus ticket; sales

Sažetak
This paper describes the applications of an enhanced neural network and genetic algorithm for bus tickets sales forecasting. The proposed approach has several significant advantages over conventional prediction methods. The major advantage of the approach is that no assumptions need to be made about the underlying function or model, since the neural network is able to extract hidden information from the historical data. Although neural networks represent a promising alternative for forecasting, the problem of network design remains and could impair widespread applications in practice. The genetic algorithm is used to evolve neural network architectures automatically, thus eliminating the pitfalls associated with human engineering approach.

Izvorni jezik
Engleski

POVEZANOST RADA