Gone in 30 Days! Predictions for Car Import Planning

Emanuel Lacic; Matthias Traub; Tomislav Duricic; Eva Haslauer; Elisabeth Lex

doi:10.1515/itit-2017-0040

Gone in 30 Days! Predictions for Car Import Planning

Emanuel Lacic^*, Matthias Traub, Tomislav Duricic, Eva Haslauer, Elisabeth Lex

^*Corresponding author for this work

Research output: Contribution to journal › Article

Abstract

A challenge for importers in the automobile industry is adjusting to rapidly changing market demands. In this work, we describe a practical study of car import planning based on the monthly car registrations in Austria. We model the task as a data driven forecasting problem and we implement four different prediction approaches. One utilizes a seasonal ARIMA model, while the other is based on LSTM-RNN and both compared to a linear and seasonal baselines. In our experiments, we evaluate the 33 different brands by predicting the number of registrations for the next month and for the year to come.

Original language	English
Pages (from-to)	219-228
Journal	IT - Information technology
Volume	60
Issue number	4
DOIs	https://doi.org/10.1515/itit-2017-0040
Publication status	Published - Aug 2018

Access to Document

10.1515/itit-2017-0040

Fingerprint Dive into the research topics of 'Gone in 30 Days! Predictions for Car Import Planning'. Together they form a unique fingerprint.

Cite this

@article{cfe0362ca55945b9959795109d369bfa,

title = "Gone in 30 Days! Predictions for Car Import Planning",

abstract = "A challenge for importers in the automobile industry is adjusting to rapidly changing market demands. In this work, we describe a practical study of car import planning based on the monthly car registrations in Austria. We model the task as a data driven forecasting problem and we implement four different prediction approaches. One utilizes a seasonal ARIMA model, while the other is based on LSTM-RNN and both compared to a linear and seasonal baselines. In our experiments, we evaluate the 33 different brands by predicting the number of registrations for the next month and for the year to come.",

author = "Emanuel Lacic and Matthias Traub and Tomislav Duricic and Eva Haslauer and Elisabeth Lex",

year = "2018",

month = "8",

doi = "10.1515/itit-2017-0040",

language = "English",

volume = "60",

pages = "219--228",

journal = "IT - Information technology",

issn = "1611-2776",

publisher = "De Gruyter Oldenbourg",

number = "4",

}

TY - JOUR

T1 - Gone in 30 Days! Predictions for Car Import Planning

AU - Lacic, Emanuel

AU - Traub, Matthias

AU - Duricic, Tomislav

AU - Haslauer, Eva

AU - Lex, Elisabeth

PY - 2018/8

Y1 - 2018/8

N2 - A challenge for importers in the automobile industry is adjusting to rapidly changing market demands. In this work, we describe a practical study of car import planning based on the monthly car registrations in Austria. We model the task as a data driven forecasting problem and we implement four different prediction approaches. One utilizes a seasonal ARIMA model, while the other is based on LSTM-RNN and both compared to a linear and seasonal baselines. In our experiments, we evaluate the 33 different brands by predicting the number of registrations for the next month and for the year to come.

AB - A challenge for importers in the automobile industry is adjusting to rapidly changing market demands. In this work, we describe a practical study of car import planning based on the monthly car registrations in Austria. We model the task as a data driven forecasting problem and we implement four different prediction approaches. One utilizes a seasonal ARIMA model, while the other is based on LSTM-RNN and both compared to a linear and seasonal baselines. In our experiments, we evaluate the 33 different brands by predicting the number of registrations for the next month and for the year to come.

U2 - 10.1515/itit-2017-0040

DO - 10.1515/itit-2017-0040

M3 - Article

VL - 60

SP - 219

EP - 228

JO - IT - Information technology

JF - IT - Information technology

SN - 1611-2776

IS - 4

ER -