Naslov
A clustering model for time-series forecasting

Autori
Čorić, Rebeka ; Đumić, Mateja ; Jelić, Slobodan

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

Izvornik
42nd International Convention - MIPRO 2019 / Skala, Karolj - Rijeka : Hrvatska udruga za informacijsku i komunikacijsku tehnologiju, elektroniku i mikroelektroniku - MIPRO, 2019, 1295-1299

Skup
42nd International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO 2019)

Mjesto i datum
Opatija, Hrvatska, 20.05.2019. - 24.05.2019

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Integer programming, clustering, k-means algorithm, heuristic, time-series forecasting, short-term prediction of airborne pollen

Sažetak
In this paper we consider a novel Integer programming approach for the cluster-based model used for time-series forecasting. There are several approaches in literature that aim to find a set of patterns which represent similar situations in the time series. In order to predict target variable, different types of fitting methods can be applied to set of data that belongs to the same pattern. We propose method that uses clustering of patterns and prediction of target value as the mean of values in the same cluster, in order to minimize total squared deviation between predicted and real values of target variable. We also propose a heuristic method that achieves good solution in practice. Our approach is applied to short-term prediction of airborne pollen concentrations. We give experimental results about comparison of our method to some common approaches.

Izvorni jezik
Engleski

Znanstvena područja
Matematika, Računarstvo

POVEZANOST RADA