Exploring the Impact of Machine Learning and AI on Inflation Prediction: A Bibliometric Approach

This study conducts a bibliometric analysis of inflation prediction, with a focus on assessing the impact of machine learning (ML) techniques. Utilizing a dataset comprising 1,651 publications sourced from Dimensions spanning the period 1975 to 2023, the research employs a comprehensive scientometric approach encompassing publications, authors, citations, references, and geographical distribution. A bibliographic co-citation network is included, and keyword analysis is performed through the Bidirectional Encoder Representations from Transformers (BERT) model, enabling the classification of papers based on their utilization of ML methods. Results indicate a notable increase in annual production from 2020 onwards. The network visually shows the most outstanding publications and keyword extraction aiding in the identification of relevant topics. While ML approaches are evident in the empirical literature, the prevalence of theoretical and enhanced econometric methods underscores the remaining challenges in fully integrating Artificial Intelligence (AI) paradigms into the field of knowledge.