Skip to main content

Research Repository

Advanced Search

Analyst-driven XAI for time series forecasting: Analytics for telecoms maintenance

Barrett, James; Legg, Phil; Smith, Jim; Boyle, Chip

Authors

Profile Image

Jim Smith James.Smith@uwe.ac.uk
Professor in Interactive Artificial Intelligence

Chip Boyle



Abstract

Time series forecasting facilitates real-time anomaly detection in telecom networks, predicting events that disrupt security and service. Current research efforts have been found to focus on new forecasting libraries, more rigorous data cleaning methods, and model hyperparameter tuning, although we believe human in-the-loop system approaches are not well applied to the domain of time series forecasting. We explore the usage of a model investigation tool to enable an interactive machine learning process that allows the interrogation of modern forecasting models to enable effective model management techniques. This research aims to demonstrate the usage of an interactive forecasting ensemble tool that enables a user to interrogate time series data, uncover insights in data predictions to make choices, and adjust a model accordingly. Through comparative testing and an analysis of existing model management strategies, we propose that enabling greater levels human-machine teaming via our tool promotes the ability to "catch" mistakes and oversights based on the assumptions of existing time series forecasting methods.

Citation

Barrett, J., Legg, P., Smith, J., & Boyle, C. (in press). Analyst-driven XAI for time series forecasting: Analytics for telecoms maintenance.

Conference Name 2024 9th International Conference on Machine Learning Technologies
Conference Location Oslo, Norway
Start Date May 24, 2024
End Date May 26, 2024
Acceptance Date Jan 19, 2024
Deposit Date Feb 28, 2024
Keywords Time Series Forecasting; Anomaly Detection; Human-in-the-Loop Machine Learning; Explainable Artificial Intelligence; Telecoms Data Analysis
Public URL https://uwe-repository.worktribe.com/output/11749855
Publisher URL https://www.icmlt.org/