An Extreme Gradient Boosting Model Optimized with Genetic Algorithm for Sales Forecasting of Retail Stores

Aziz Kemal Konyalıoğlu; Tuğçe Beldek Apaydın; İlhan Turhan; Adil Soydal; Tuncay Özcan

doi:10.1007/978-3-031-53991-6_5

An Extreme Gradient Boosting Model Optimized with Genetic Algorithm for Sales Forecasting of Retail Stores

Aziz Kemal Konyalıoğlu^*, Tuğçe Beldek Apaydın, İlhan Turhan, Adil Soydal, Tuncay Özcan

^*Corresponding author for this work

Department of Management Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Forecasting has always been a curious topic to investigate for practitioners, academics and workers in private companies. Not only in the world but also In Turkey, COVID-19 pandemic makes difficult to forecast sales for any type of companies since patterns, sales and seasonality factors in sales have changed because of different reasons. At this point, the accuracy of sales forecasts is of great importance for retail companies. In particular, sales forecasts affect the decisions and actions taken on a daily and weekly basis. In this study, firstly, a model based on the Extreme Gradient Boosting (XGBoost) algorithm is proposed for daily sales forecasting of retail stores. Later, a hybrid GA-XGBoost model is developed to improve the performance of this model. In this model, the parameters of XGBoost are optimized by Genetic Algorithm. Finally, the performance of the developed model is compared with the SARIMA model using the root mean square error (RMSE), mean absolute percentage error (MAPE) and R-squared. The performance comparison is demonstrated by a case study with data from airport stores of a retail chain in Turkey. Numerical results show that the hybrid XGBoost-GA model outperforms the XGBoost and SARIMA models.

Original language	English
Title of host publication	Industrial Engineering in the Industry 4.0 Era - Selected Papers from ISPR2023
Editors	Numan M. Durakbasa, M. Güneş Gençyılmaz
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	59-67
Number of pages	9
ISBN (Print)	9783031539909
DOIs	https://doi.org/10.1007/978-3-031-53991-6_5
Publication status	Published - 2024
Event	International Symposium for Production Research, ISPR 2023 - Antalya, Turkey Duration: 5 Oct 2023 → 7 Oct 2023

Publication series

Name	Lecture Notes in Mechanical Engineering
ISSN (Print)	2195-4356
ISSN (Electronic)	2195-4364

Conference

Conference	International Symposium for Production Research, ISPR 2023
Country/Territory	Turkey
City	Antalya
Period	5/10/23 → 7/10/23

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

Keywords

Extreme Gradient Boosting
Genetic Algorithm
Retailing
Sales Forecasting

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-031-53991-6_5

Cite this

Konyalıoğlu, A. K., Apaydın, T. B., Turhan, İ., Soydal, A., & Özcan, T. (2024). An Extreme Gradient Boosting Model Optimized with Genetic Algorithm for Sales Forecasting of Retail Stores. In N. M. Durakbasa, & M. G. Gençyılmaz (Eds.), Industrial Engineering in the Industry 4.0 Era - Selected Papers from ISPR2023 (pp. 59-67). (Lecture Notes in Mechanical Engineering). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-53991-6_5

Konyalıoğlu, Aziz Kemal ; Apaydın, Tuğçe Beldek ; Turhan, İlhan et al. / An Extreme Gradient Boosting Model Optimized with Genetic Algorithm for Sales Forecasting of Retail Stores. Industrial Engineering in the Industry 4.0 Era - Selected Papers from ISPR2023. editor / Numan M. Durakbasa ; M. Güneş Gençyılmaz. Springer Science and Business Media Deutschland GmbH, 2024. pp. 59-67 (Lecture Notes in Mechanical Engineering).

@inproceedings{b14c7b03ffc44911a64141fcd03f70a3,

title = "An Extreme Gradient Boosting Model Optimized with Genetic Algorithm for Sales Forecasting of Retail Stores",

abstract = "Forecasting has always been a curious topic to investigate for practitioners, academics and workers in private companies. Not only in the world but also In Turkey, COVID-19 pandemic makes difficult to forecast sales for any type of companies since patterns, sales and seasonality factors in sales have changed because of different reasons. At this point, the accuracy of sales forecasts is of great importance for retail companies. In particular, sales forecasts affect the decisions and actions taken on a daily and weekly basis. In this study, firstly, a model based on the Extreme Gradient Boosting (XGBoost) algorithm is proposed for daily sales forecasting of retail stores. Later, a hybrid GA-XGBoost model is developed to improve the performance of this model. In this model, the parameters of XGBoost are optimized by Genetic Algorithm. Finally, the performance of the developed model is compared with the SARIMA model using the root mean square error (RMSE), mean absolute percentage error (MAPE) and R-squared. The performance comparison is demonstrated by a case study with data from airport stores of a retail chain in Turkey. Numerical results show that the hybrid XGBoost-GA model outperforms the XGBoost and SARIMA models.",

keywords = "Extreme Gradient Boosting, Genetic Algorithm, Retailing, Sales Forecasting",

author = "Konyalıoğlu, {Aziz Kemal} and Apaydın, {Tuğ{\c c}e Beldek} and İlhan Turhan and Adil Soydal and Tuncay {\"O}zcan",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.; International Symposium for Production Research, ISPR 2023 ; Conference date: 05-10-2023 Through 07-10-2023",

year = "2024",

doi = "10.1007/978-3-031-53991-6_5",

language = "English",

isbn = "9783031539909",

series = "Lecture Notes in Mechanical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "59--67",

editor = "Durakbasa, {Numan M.} and Gen{\c c}yılmaz, {M. G{\"u}ne{\c s}}",

booktitle = "Industrial Engineering in the Industry 4.0 Era - Selected Papers from ISPR2023",

address = "Germany",

}

Konyalıoğlu, AK, Apaydın, TB, Turhan, İ, Soydal, A & Özcan, T 2024, An Extreme Gradient Boosting Model Optimized with Genetic Algorithm for Sales Forecasting of Retail Stores. in NM Durakbasa & MG Gençyılmaz (eds), Industrial Engineering in the Industry 4.0 Era - Selected Papers from ISPR2023. Lecture Notes in Mechanical Engineering, Springer Science and Business Media Deutschland GmbH, pp. 59-67, International Symposium for Production Research, ISPR 2023, Antalya, Turkey, 5/10/23. https://doi.org/10.1007/978-3-031-53991-6_5

An Extreme Gradient Boosting Model Optimized with Genetic Algorithm for Sales Forecasting of Retail Stores. / Konyalıoğlu, Aziz Kemal; Apaydın, Tuğçe Beldek; Turhan, İlhan et al.
Industrial Engineering in the Industry 4.0 Era - Selected Papers from ISPR2023. ed. / Numan M. Durakbasa; M. Güneş Gençyılmaz. Springer Science and Business Media Deutschland GmbH, 2024. p. 59-67 (Lecture Notes in Mechanical Engineering).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - An Extreme Gradient Boosting Model Optimized with Genetic Algorithm for Sales Forecasting of Retail Stores

AU - Konyalıoğlu, Aziz Kemal

AU - Apaydın, Tuğçe Beldek

AU - Turhan, İlhan

AU - Soydal, Adil

AU - Özcan, Tuncay

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

PY - 2024

Y1 - 2024

N2 - Forecasting has always been a curious topic to investigate for practitioners, academics and workers in private companies. Not only in the world but also In Turkey, COVID-19 pandemic makes difficult to forecast sales for any type of companies since patterns, sales and seasonality factors in sales have changed because of different reasons. At this point, the accuracy of sales forecasts is of great importance for retail companies. In particular, sales forecasts affect the decisions and actions taken on a daily and weekly basis. In this study, firstly, a model based on the Extreme Gradient Boosting (XGBoost) algorithm is proposed for daily sales forecasting of retail stores. Later, a hybrid GA-XGBoost model is developed to improve the performance of this model. In this model, the parameters of XGBoost are optimized by Genetic Algorithm. Finally, the performance of the developed model is compared with the SARIMA model using the root mean square error (RMSE), mean absolute percentage error (MAPE) and R-squared. The performance comparison is demonstrated by a case study with data from airport stores of a retail chain in Turkey. Numerical results show that the hybrid XGBoost-GA model outperforms the XGBoost and SARIMA models.

AB - Forecasting has always been a curious topic to investigate for practitioners, academics and workers in private companies. Not only in the world but also In Turkey, COVID-19 pandemic makes difficult to forecast sales for any type of companies since patterns, sales and seasonality factors in sales have changed because of different reasons. At this point, the accuracy of sales forecasts is of great importance for retail companies. In particular, sales forecasts affect the decisions and actions taken on a daily and weekly basis. In this study, firstly, a model based on the Extreme Gradient Boosting (XGBoost) algorithm is proposed for daily sales forecasting of retail stores. Later, a hybrid GA-XGBoost model is developed to improve the performance of this model. In this model, the parameters of XGBoost are optimized by Genetic Algorithm. Finally, the performance of the developed model is compared with the SARIMA model using the root mean square error (RMSE), mean absolute percentage error (MAPE) and R-squared. The performance comparison is demonstrated by a case study with data from airport stores of a retail chain in Turkey. Numerical results show that the hybrid XGBoost-GA model outperforms the XGBoost and SARIMA models.

KW - Extreme Gradient Boosting

KW - Genetic Algorithm

KW - Retailing

KW - Sales Forecasting

UR - http://www.scopus.com/inward/record.url?scp=85187797294&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-53991-6_5

DO - 10.1007/978-3-031-53991-6_5

M3 - Conference contribution

AN - SCOPUS:85187797294

SN - 9783031539909

T3 - Lecture Notes in Mechanical Engineering

SP - 59

EP - 67

BT - Industrial Engineering in the Industry 4.0 Era - Selected Papers from ISPR2023

A2 - Durakbasa, Numan M.

A2 - Gençyılmaz, M. Güneş

PB - Springer Science and Business Media Deutschland GmbH

T2 - International Symposium for Production Research, ISPR 2023

Y2 - 5 October 2023 through 7 October 2023

ER -

Konyalıoğlu AK, Apaydın TB, Turhan İ, Soydal A, Özcan T. An Extreme Gradient Boosting Model Optimized with Genetic Algorithm for Sales Forecasting of Retail Stores. In Durakbasa NM, Gençyılmaz MG, editors, Industrial Engineering in the Industry 4.0 Era - Selected Papers from ISPR2023. Springer Science and Business Media Deutschland GmbH. 2024. p. 59-67. (Lecture Notes in Mechanical Engineering). doi: 10.1007/978-3-031-53991-6_5

An Extreme Gradient Boosting Model Optimized with Genetic Algorithm for Sales Forecasting of Retail Stores

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this