Influence of Car Configurator Webpage Data from Automotive Manufacturers on Car Sales by Means of Correlation and Forecasting

Juan Manuel García Sánchez; Xavier Vilasís Cardona; Alexandre Lerma Martín

doi:10.3390/forecast4030034

Influence of Car Configurator Webpage Data from Automotive Manufacturers on Car Sales by Means of Correlation and Forecasting

Juan Manuel García Sánchez
, Xavier Vilasís Cardona
, Alexandre Lerma Martín

Research output: Indexed journal article › Article › peer-review

2 Citations (Scopus)

Abstract

A methodology to prove the influence of car configurator webpage data for automotive manufacturers is developed across this research. Firstly, the correlation between online data and sales is measured. Afterward, car variant sales are predicted using a set of forecasting techniques divided into univariate and multivariate ones. Finally, weekly color mix sales based on these techniques are built and compared. Results show that users visit car configurator webpages 1 to 6 months before the purchase date. Additionally, car variants predictions and weekly color mix sales derived from multivariate techniques, i.e., using car configurator data as external input, provide improvement up to 25 points in the assessment metric.

Original language	English
Pages (from-to)	634-653
Number of pages	20
Journal	Forecasting
Volume	4
Issue number	3
DOIs	https://doi.org/10.3390/forecast4030034
Publication status	Published - Sept 2022

Keywords

automotive OEMs
car configurator data
forecasting
machine learning
Pearson correlation coefficient
prediction
time series
weekly color mix sales

Access to Document

10.3390/forecast4030034

Cite this

@article{df46c7a836894725a970998939e15b00,

title = "Influence of Car Configurator Webpage Data from Automotive Manufacturers on Car Sales by Means of Correlation and Forecasting",

abstract = "A methodology to prove the influence of car configurator webpage data for automotive manufacturers is developed across this research. Firstly, the correlation between online data and sales is measured. Afterward, car variant sales are predicted using a set of forecasting techniques divided into univariate and multivariate ones. Finally, weekly color mix sales based on these techniques are built and compared. Results show that users visit car configurator webpages 1 to 6 months before the purchase date. Additionally, car variants predictions and weekly color mix sales derived from multivariate techniques, i.e., using car configurator data as external input, provide improvement up to 25 points in the assessment metric.",

keywords = "automotive OEMs, car configurator data, forecasting, machine learning, Pearson correlation coefficient, prediction, time series, weekly color mix sales",

author = "\{Garc{\'i}a S{\'a}nchez\}, \{Juan Manuel\} and \{Vilas{\'i}s Cardona\}, Xavier and \{Lerma Mart{\'i}n\}, Alexandre",

note = "Funding Information: This work is partially funded by the Department de Recerca i Universitats of the Generalitat de Catalunya under the Industrial Doctorate Grant DI 2019-34. Publisher Copyright: {\textcopyright} 2022 by the authors.",

year = "2022",

month = sep,

doi = "10.3390/forecast4030034",

language = "English",

volume = "4",

pages = "634--653",

journal = "Forecasting",

issn = "2571-9394",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "3",

}

TY - JOUR

T1 - Influence of Car Configurator Webpage Data from Automotive Manufacturers on Car Sales by Means of Correlation and Forecasting

AU - García Sánchez, Juan Manuel

AU - Vilasís Cardona, Xavier

AU - Lerma Martín, Alexandre

N1 - Funding Information: This work is partially funded by the Department de Recerca i Universitats of the Generalitat de Catalunya under the Industrial Doctorate Grant DI 2019-34. Publisher Copyright: © 2022 by the authors.

PY - 2022/9

Y1 - 2022/9

N2 - A methodology to prove the influence of car configurator webpage data for automotive manufacturers is developed across this research. Firstly, the correlation between online data and sales is measured. Afterward, car variant sales are predicted using a set of forecasting techniques divided into univariate and multivariate ones. Finally, weekly color mix sales based on these techniques are built and compared. Results show that users visit car configurator webpages 1 to 6 months before the purchase date. Additionally, car variants predictions and weekly color mix sales derived from multivariate techniques, i.e., using car configurator data as external input, provide improvement up to 25 points in the assessment metric.

AB - A methodology to prove the influence of car configurator webpage data for automotive manufacturers is developed across this research. Firstly, the correlation between online data and sales is measured. Afterward, car variant sales are predicted using a set of forecasting techniques divided into univariate and multivariate ones. Finally, weekly color mix sales based on these techniques are built and compared. Results show that users visit car configurator webpages 1 to 6 months before the purchase date. Additionally, car variants predictions and weekly color mix sales derived from multivariate techniques, i.e., using car configurator data as external input, provide improvement up to 25 points in the assessment metric.

KW - automotive OEMs

KW - car configurator data

KW - forecasting

KW - machine learning

KW - Pearson correlation coefficient

KW - prediction

KW - time series

KW - weekly color mix sales

UR - https://www.scopus.com/pages/publications/85164494937

U2 - 10.3390/forecast4030034

DO - 10.3390/forecast4030034

M3 - Article

AN - SCOPUS:85164494937

SN - 2571-9394

VL - 4

SP - 634

EP - 653

JO - Forecasting

JF - Forecasting

IS - 3

ER -

Influence of Car Configurator Webpage Data from Automotive Manufacturers on Car Sales by Means of Correlation and Forecasting

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this