Explainable artificial intelligence (XAI) provides explana- tions for not interpretable machine learning (ML) models. While many technical approaches exist, there is a lack of validation of these techniques on real-world datasets. In this work, we present a use-case of XAI: an ML model which is trained to estimate electrification rates based on mobile phone data in Senegal. The data originate from the Data for Develop- ment challenge by Orange in 2014/15. We apply two model-agnostic, local explanation techniques and find that while the model can be veri- fied, it is biased with respect to the population density. We conclude our paper by pointing to the two main challenges we encountered during our work: data processing and model design that might be restricted by cur- rently available XAI methods, and the importance of domain knowledge to interpret explanations.

Explainability in Practice : Estimating Electrification Rates from Mobile Phone Data in Senegal

State, Laura;
2023

Abstract

Explainable artificial intelligence (XAI) provides explana- tions for not interpretable machine learning (ML) models. While many technical approaches exist, there is a lack of validation of these techniques on real-world datasets. In this work, we present a use-case of XAI: an ML model which is trained to estimate electrification rates based on mobile phone data in Senegal. The data originate from the Data for Develop- ment challenge by Orange in 2014/15. We apply two model-agnostic, local explanation techniques and find that while the model can be veri- fied, it is biased with respect to the population density. We conclude our paper by pointing to the two main challenges we encountered during our work: data processing and model design that might be restricted by cur- rently available XAI methods, and the importance of domain knowledge to interpret explanations.
2023
Settore INF/01 - Informatica
World Conference on Explainable Artificial Intelligence
explainable AI; Use-case; Mobile Phone Data; Global South
File in questo prodotto:
File Dimensione Formato  
state_explainability_in_practice.pdf

accesso aperto

Descrizione: Explainability in Practice: Estimating Electrification Rates from Mobile Phone Data in Senegal
Tipologia: Submitted version (pre-print)
Licenza: Solo Lettura
Dimensione 2.91 MB
Formato Adobe PDF
2.91 MB Adobe PDF
state_explainability_in_practice.pdf

Accesso chiuso

Descrizione: Explainability in Practice: Estimating Electrification Rates from Mobile Phone Data in Senegal
Tipologia: Published version
Licenza: Non pubblico
Dimensione 1.85 MB
Formato Adobe PDF
1.85 MB Adobe PDF   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11384/140502
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact