Explainable AI: Investigating Transformer, NBeats, and LSTM models for Inflation Forecasting Economic Indicators

Bathula, Pradeep Kumar Reddy (2023) Explainable AI: Investigating Transformer, NBeats, and LSTM models for Inflation Forecasting Economic Indicators. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

Our research examines the application of Explainable Artificial Intelligence (XAI) principles to understand how sophisticated machine learning models, such as Trans- form, NBeats, along with LSTM, anticipate rising prices. It utilizes key economic indicators such as Personal Consumption Expenditures (PCE), Producer Price Index (PPI), Gross Domestic Product (GDP), and Consume r Price Index (CPI). Main objective is understanding how algorithms interpret and incorporate economic data into their predictions. This will increase our understanding of complex eco- nomic forecasting processes. Research uses XAI for determining how each economic indicator improves algorithms’ forecast accuracy. This technique lets us compare model computing capabilities to determine relative importance of PCE, PPI, GDP, CPI into inflation estimates. Our results underscore the relevance of components to improving prediction accuracy through explaining underlying model concepts. This investigation expands to explore AI models in economic research. Research using XAI improves economic decision- making by providing clear and understandable AI-driven forecasting results. Our study stresses explaining the ability in using AI models for complicated economic projections to contribute to the fast- growing area of AI in economics. It also stresses openness and honesty whereas using AI for complex economic forecasting and research.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Anant, Aaloka UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence Q Science > QA Mathematics > Algebra > Algorithms > Computer algorithms H Social Sciences > Economics
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	07 May 2025 10:50
Last Modified:	07 May 2025 10:50
URI:	https://norma.ncirl.ie/id/eprint/7497

Actions (login required)

View Item