Naslov
Customer Segmentation Using Neural Networks

Autori
Ćorić Dajana ; Ćurko Katarina ; Varga Mladen

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings od 9th International Conference on Computer Engineering and Applications (CEA15) / - Dubai, 2015, 162-169

Skup
9th International Conference on Computer Engineering and Applications (CEA15)

Mjesto i datum
Dubai, Ujedinjeni Arapski Emirati, 22.02.2015. - 24.02.2015

Vrsta sudjelovanja
Pozvano predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
customer; profitability; neural networks

Sažetak
This paper shows how neural networks can be useful in process of predicting customer segments. Customer segmentation provides to companies insight in differentiating profitable from non-profitable customers so that companies can act properly on each group. The aim of this paper is to determine how neural networks are able to predict belonging of each customer to specific segment based on data from data warehouse. This paper presents research on analysing data set of customers of the company which take care of production and distribution of the range of products from a set of nuts, grains and dried fruit. As a result will be three groups of customers: group containing the most profitable customers, group of customers with a profit close to zero, and group of the least profitable customers. Depending on where specific customer belongs, company will use different marketing activities in order to retain them, move them to more profitable segment or ultimately reject them. Customer activity in first quarter will be used to predict segment in which customer belongs at the end of the year. This will show predictive ability of neural networks and how reliable they are in process of customer segmentation using incomplete data.

Izvorni jezik
Engleski

Znanstvena područja
Ekonomija, Informacijske i komunikacijske znanosti

POVEZANOST RADA