Implementation Of Machine Learning and BPM To Increase Profitability in A Travel Agency

Guillermo Huapalla; Aiko Makino; Edilberto Miguel Avalos Ortecho

doi:10.11159/icmie25.128

Implementation Of Machine Learning and BPM To Increase Profitability in A Travel Agency

Guillermo Huapalla
, Aiko Makino
, Edilberto Miguel Avalos Ortecho

Industrial Engineering School

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

Abstract

This research addresses the low accuracy in monthly tourist projections for a travel agency, with a Mean Absolute Percentage
Error (MAPE) of 29.49%, resulting in an opportunity cost of $3.9 million in the travel package purchasing process. A solution was
implemented using Machine Learning (ML) techniques, Support Vector Regression - Seasonal Autoregressive Integrated Moving
Average with Exogenous Regressors (SVR-SARIMAX), and Business Process Management (BPM) to reduce the MAPE and improve
the purchasing process by redesigning and adding a negotiation activity. The ML model was trained on historical data of international
tourist arrivals from 2013 to 2023, and 2023 purchase records. Using Python and Arena software, the MAPE was reduced to 18.18%,
with key performance indicators improving by 16%, reaching 19,907 customers, $20.7 million in revenue, and $1.8 million in opportunity
cost. Furthermore, a conversion rate over 90% was achieved after implementing process improvements, demonstrating the effectiveness
of ML and BPM in resource allocation and process enhancement.

Original language	English
Title of host publication	Proceedings of the 11th World Congress on Mechanical, Chemical, and Material Engineering, MCM 2025
Editors	Huihe Qiu, Yuwen Zhang, Marcello Iasiello
Pages	128-1
Number of pages	8
DOIs	https://doi.org/10.11159/icmie25.128
State	Published - 12 Aug 2025

Publication series

Name	Proceedings of the World Congress on Mechanical, Chemical, and Material Engineering
ISSN (Electronic)	2369-8136

Keywords

Business Process Management (BPM)
Machine Learning (ML)
Support Vector Regression-Seasonal Autoregressive Integrated Moving Average with Exogenous Regressors (SVR-SARIMAX)
tourism

Access to Document

10.11159/icmie25.128License: Unspecified

Cite this

Huapalla, G., Makino, A., & Avalos Ortecho, E. M. (2025). Implementation Of Machine Learning and BPM To Increase Profitability in A Travel Agency. In H. Qiu, Y. Zhang, & M. Iasiello (Eds.), Proceedings of the 11th World Congress on Mechanical, Chemical, and Material Engineering, MCM 2025 (pp. 128-1). Article 128 (Proceedings of the World Congress on Mechanical, Chemical, and Material Engineering). https://doi.org/10.11159/icmie25.128

Huapalla, Guillermo ; Makino, Aiko ; Avalos Ortecho, Edilberto Miguel. / Implementation Of Machine Learning and BPM To Increase Profitability in A Travel Agency. Proceedings of the 11th World Congress on Mechanical, Chemical, and Material Engineering, MCM 2025. editor / Huihe Qiu ; Yuwen Zhang ; Marcello Iasiello. 2025. pp. 128-1 (Proceedings of the World Congress on Mechanical, Chemical, and Material Engineering).

@inproceedings{0cc56771471049038e0ca3a0de636a6e,

title = "Implementation Of Machine Learning and BPM To Increase Profitability in A Travel Agency",

abstract = "This research addresses the low accuracy in monthly tourist projections for a travel agency, with a Mean Absolute Percentage Error (MAPE) of 29.49\%, resulting in an opportunity cost of \$3.9 million in the travel package purchasing process. A solution was implemented using Machine Learning (ML) techniques, Support Vector Regression - Seasonal Autoregressive Integrated Moving Average with Exogenous Regressors (SVR-SARIMAX), and Business Process Management (BPM) to reduce the MAPE and improve the purchasing process by redesigning and adding a negotiation activity. The ML model was trained on historical data of international tourist arrivals from 2013 to 2023, and 2023 purchase records. Using Python and Arena software, the MAPE was reduced to 18.18\%, with key performance indicators improving by 16\%, reaching 19,907 customers, \$20.7 million in revenue, and \$1.8 million in opportunity cost. Furthermore, a conversion rate over 90\% was achieved after implementing process improvements, demonstrating the effectiveness of ML and BPM in resource allocation and process enhancement.",

keywords = "Business Process Management (BPM), Machine Learning (ML), Support Vector Regression-Seasonal Autoregressive Integrated Moving Average with Exogenous Regressors (SVR-SARIMAX), tourism",

author = "Guillermo Huapalla and Aiko Makino and \{Avalos Ortecho\}, \{Edilberto Miguel\}",

year = "2025",

month = aug,

day = "12",

doi = "10.11159/icmie25.128",

language = "Ingl{\'e}s",

isbn = "9781990800603",

series = "Proceedings of the World Congress on Mechanical, Chemical, and Material Engineering",

pages = "128--1",

editor = "Huihe Qiu and Yuwen Zhang and Marcello Iasiello",

booktitle = "Proceedings of the 11th World Congress on Mechanical, Chemical, and Material Engineering, MCM 2025",

}

Huapalla, G, Makino, A & Avalos Ortecho, EM 2025, Implementation Of Machine Learning and BPM To Increase Profitability in A Travel Agency. in H Qiu, Y Zhang & M Iasiello (eds), Proceedings of the 11th World Congress on Mechanical, Chemical, and Material Engineering, MCM 2025., 128, Proceedings of the World Congress on Mechanical, Chemical, and Material Engineering, pp. 128-1. https://doi.org/10.11159/icmie25.128

Implementation Of Machine Learning and BPM To Increase Profitability in A Travel Agency. / Huapalla, Guillermo; Makino, Aiko; Avalos Ortecho, Edilberto Miguel.
Proceedings of the 11th World Congress on Mechanical, Chemical, and Material Engineering, MCM 2025. ed. / Huihe Qiu; Yuwen Zhang; Marcello Iasiello. 2025. p. 128-1 128 (Proceedings of the World Congress on Mechanical, Chemical, and Material Engineering).

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

TY - GEN

T1 - Implementation Of Machine Learning and BPM To Increase Profitability in A Travel Agency

AU - Huapalla, Guillermo

AU - Makino, Aiko

AU - Avalos Ortecho, Edilberto Miguel

PY - 2025/8/12

Y1 - 2025/8/12

N2 - This research addresses the low accuracy in monthly tourist projections for a travel agency, with a Mean Absolute Percentage Error (MAPE) of 29.49%, resulting in an opportunity cost of $3.9 million in the travel package purchasing process. A solution was implemented using Machine Learning (ML) techniques, Support Vector Regression - Seasonal Autoregressive Integrated Moving Average with Exogenous Regressors (SVR-SARIMAX), and Business Process Management (BPM) to reduce the MAPE and improve the purchasing process by redesigning and adding a negotiation activity. The ML model was trained on historical data of international tourist arrivals from 2013 to 2023, and 2023 purchase records. Using Python and Arena software, the MAPE was reduced to 18.18%, with key performance indicators improving by 16%, reaching 19,907 customers, $20.7 million in revenue, and $1.8 million in opportunity cost. Furthermore, a conversion rate over 90% was achieved after implementing process improvements, demonstrating the effectiveness of ML and BPM in resource allocation and process enhancement.

AB - This research addresses the low accuracy in monthly tourist projections for a travel agency, with a Mean Absolute Percentage Error (MAPE) of 29.49%, resulting in an opportunity cost of $3.9 million in the travel package purchasing process. A solution was implemented using Machine Learning (ML) techniques, Support Vector Regression - Seasonal Autoregressive Integrated Moving Average with Exogenous Regressors (SVR-SARIMAX), and Business Process Management (BPM) to reduce the MAPE and improve the purchasing process by redesigning and adding a negotiation activity. The ML model was trained on historical data of international tourist arrivals from 2013 to 2023, and 2023 purchase records. Using Python and Arena software, the MAPE was reduced to 18.18%, with key performance indicators improving by 16%, reaching 19,907 customers, $20.7 million in revenue, and $1.8 million in opportunity cost. Furthermore, a conversion rate over 90% was achieved after implementing process improvements, demonstrating the effectiveness of ML and BPM in resource allocation and process enhancement.

KW - Business Process Management (BPM)

KW - Machine Learning (ML)

KW - Support Vector Regression-Seasonal Autoregressive Integrated Moving Average with Exogenous Regressors (SVR-SARIMAX)

KW - tourism

UR - https://www.scopus.com/pages/publications/105021839335

U2 - 10.11159/icmie25.128

DO - 10.11159/icmie25.128

M3 - Articulo (Contribución a conferencia)

SN - 9781990800603

T3 - Proceedings of the World Congress on Mechanical, Chemical, and Material Engineering

SP - 128

EP - 121

BT - Proceedings of the 11th World Congress on Mechanical, Chemical, and Material Engineering, MCM 2025

A2 - Qiu, Huihe

A2 - Zhang, Yuwen

A2 - Iasiello, Marcello

ER -

Huapalla G, Makino A, Avalos Ortecho EM. Implementation Of Machine Learning and BPM To Increase Profitability in A Travel Agency. In Qiu H, Zhang Y, Iasiello M, editors, Proceedings of the 11th World Congress on Mechanical, Chemical, and Material Engineering, MCM 2025. 2025. p. 128-1. 128. (Proceedings of the World Congress on Mechanical, Chemical, and Material Engineering). doi: 10.11159/icmie25.128

Implementation Of Machine Learning and BPM To Increase Profitability in A Travel Agency

Abstract

Publication series

Keywords

Access to Document

Other files and links

Cite this