Towards Trustworthy AI in Demand Planning: Defining Explainability for Supply Chain Management

Ruiqi Zhu; Cecilie Christensen; Bahram Zarrin; Per Bækgaard; Tommy Sonne Alstrøm

doi:10.5220/0013315900003890

Towards Trustworthy AI in Demand Planning: Defining Explainability for Supply Chain Management

Ruiqi Zhu, Cecilie Christensen, Bahram Zarrin, Per Bækgaard, Tommy Sonne Alstrøm

Microsoft Development Center Copenhagen

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

32 Downloads (Orbit)

Abstract

Artificial intelligence is increasingly essential in supply chain management, where machine learning models improve demand forecasting accuracy. However, as AI usage expands, so does the complexity and opacity
of predictive models. Given the significant impact on operations, it is crucial for demand planners to trust these forecasts and the decisions derived from them, highlighting the need for explainability. This paper
reviews prominent definitions of explainability in AI and proposes a tailored definition of explainability for supply chain management. By using a user-centric approach, we address the practical needs of definitions of
explainability for non-technical users. This domain-specific definition aims to support the future development of interpretable AI models that enhance user trust and usability in demand planning tools.

Original language	English
Title of host publication	Proceedings of the 17th International Conference on Agents and Artificial Intelligence (ICAART 2025)
Volume	3
Publisher	SCITEPRESS Digital Library
Publication date	2025
Pages	1245-1253
ISBN (Electronic)	978-989-758-737-5
DOIs	https://doi.org/10.5220/0013315900003890
Publication status	Published - 2025
Event	17th International Conference on Agents and Artificial Intelligence - Porto, Portugal Duration: 23 Feb 2025 → 25 Feb 2025

Conference

Conference	17th International Conference on Agents and Artificial Intelligence
Country/Territory	Portugal
City	Porto
Period	23/02/2025 → 25/02/2025

Keywords

Explainable AI
Supply Chain Management
Demand Planning
User-Centric Explainability

Access to Document

10.5220/0013315900003890Licence: CC BY-NC-ND

FulltextFinal published version, 4.56 MBLicence: CC BY-NC-ND

OpenUrl availability

Full text

Cite this

Zhu, R., Christensen, C., Zarrin, B., Bækgaard, P., & Alstrøm, T. S. (2025). Towards Trustworthy AI in Demand Planning: Defining Explainability for Supply Chain Management. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence (ICAART 2025) (Vol. 3, pp. 1245-1253). SCITEPRESS Digital Library. https://doi.org/10.5220/0013315900003890

@inproceedings{26bacccd300f4c858753d263a5cc8b52,

title = "Towards Trustworthy AI in Demand Planning: Defining Explainability for Supply Chain Management",

abstract = "Artificial intelligence is increasingly essential in supply chain management, where machine learning models improve demand forecasting accuracy. However, as AI usage expands, so does the complexity and opacityof predictive models. Given the significant impact on operations, it is crucial for demand planners to trust these forecasts and the decisions derived from them, highlighting the need for explainability. This paperreviews prominent definitions of explainability in AI and proposes a tailored definition of explainability for supply chain management. By using a user-centric approach, we address the practical needs of definitions ofexplainability for non-technical users. This domain-specific definition aims to support the future development of interpretable AI models that enhance user trust and usability in demand planning tools.",

keywords = "Explainable AI, Supply Chain Management, Demand Planning, User-Centric Explainability",

author = "Ruiqi Zhu and Cecilie Christensen and Bahram Zarrin and Per B{\ae}kgaard and Alstr{\o}m, \{Tommy Sonne\}",

year = "2025",

doi = "10.5220/0013315900003890",

language = "English",

volume = "3",

pages = "1245--1253",

booktitle = "Proceedings of the 17th International Conference on Agents and Artificial Intelligence (ICAART 2025)",

publisher = "SCITEPRESS Digital Library",

note = "17th International Conference on Agents and Artificial Intelligence, ICAART ; Conference date: 23-02-2025 Through 25-02-2025",

}

Zhu, R, Christensen, C, Zarrin, B, Bækgaard, P & Alstrøm, TS 2025, Towards Trustworthy AI in Demand Planning: Defining Explainability for Supply Chain Management. in Proceedings of the 17th International Conference on Agents and Artificial Intelligence (ICAART 2025) . vol. 3, SCITEPRESS Digital Library, pp. 1245-1253, 17th International Conference on Agents and Artificial Intelligence, Porto, Portugal, 23/02/2025. https://doi.org/10.5220/0013315900003890

Towards Trustworthy AI in Demand Planning: Defining Explainability for Supply Chain Management. / Zhu, Ruiqi; Christensen, Cecilie; Zarrin, Bahram et al.
Proceedings of the 17th International Conference on Agents and Artificial Intelligence (ICAART 2025) . Vol. 3 SCITEPRESS Digital Library, 2025. p. 1245-1253.

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

TY - GEN

T1 - Towards Trustworthy AI in Demand Planning: Defining Explainability for Supply Chain Management

AU - Zhu, Ruiqi

AU - Christensen, Cecilie

AU - Zarrin, Bahram

AU - Bækgaard, Per

AU - Alstrøm, Tommy Sonne

PY - 2025

Y1 - 2025

N2 - Artificial intelligence is increasingly essential in supply chain management, where machine learning models improve demand forecasting accuracy. However, as AI usage expands, so does the complexity and opacityof predictive models. Given the significant impact on operations, it is crucial for demand planners to trust these forecasts and the decisions derived from them, highlighting the need for explainability. This paperreviews prominent definitions of explainability in AI and proposes a tailored definition of explainability for supply chain management. By using a user-centric approach, we address the practical needs of definitions ofexplainability for non-technical users. This domain-specific definition aims to support the future development of interpretable AI models that enhance user trust and usability in demand planning tools.

AB - Artificial intelligence is increasingly essential in supply chain management, where machine learning models improve demand forecasting accuracy. However, as AI usage expands, so does the complexity and opacityof predictive models. Given the significant impact on operations, it is crucial for demand planners to trust these forecasts and the decisions derived from them, highlighting the need for explainability. This paperreviews prominent definitions of explainability in AI and proposes a tailored definition of explainability for supply chain management. By using a user-centric approach, we address the practical needs of definitions ofexplainability for non-technical users. This domain-specific definition aims to support the future development of interpretable AI models that enhance user trust and usability in demand planning tools.

KW - Explainable AI

KW - Supply Chain Management

KW - Demand Planning

KW - User-Centric Explainability

U2 - 10.5220/0013315900003890

DO - 10.5220/0013315900003890

M3 - Article in proceedings

VL - 3

SP - 1245

EP - 1253

BT - Proceedings of the 17th International Conference on Agents and Artificial Intelligence (ICAART 2025)

PB - SCITEPRESS Digital Library

T2 - 17th International Conference on Agents and Artificial Intelligence

Y2 - 23 February 2025 through 25 February 2025

ER -

Towards Trustworthy AI in Demand Planning: Defining Explainability for Supply Chain Management

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this