Abstract
Inflation is one of the critical parameters that indicate a country’s economic position. Therefore, maintaining it at a stable level is one of the objectives of any country’s financial regulator. In Sri Lanka, the Central Bank of Sri Lanka (CBSL) is mandated to formulate policies to achieve desired inflation targets that reflect in price indices, mainly the Colombo Consumer Price Index (CCPI). The effectiveness of these policies depends on the accuracy of projections obtained by such CCPI models. Hence, regulators continuously attempt to develop models that are more accurate, flexible, and stable in their predictions. At present, economic data modeling has taken a new turn around the globe with the introduction of Machine Learning (ML) algorithms. ML approach, although is promising, is not yet extensively explored in the context of the Sri Lankan economy. The study attempts to address this gap by constructing six different types of tuned ML models to compare and arrive at the best model for CCPI-based inflation prediction in Sri Lanka. It also presents a rationally selected combination of predictor variables, specialized for the Sri Lankan economic environment. The results of the study indicate that support vector regression is the best model in terms of prediction power to achieve the said objective. This study also recommends it as a model that is highly flexible and resistant to any future modifications.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Behrens C, Pierdzioch C, Risse M (2018) Testing the optimality of inflation forecasts under flexible loss with random forests. Econ Model 72:03
Bukhari S, Muhammad Hanif (2007) Inflation forecasting using artificial neural networks. 8
Ali Choudhary M, Adnan Haider (2008) Neural network models for inflation forecasting: an appraisal. Appl Econ 44(12)
Enke D, Mehdiyev N (2014) A hybrid neuro-fuzzy model to forecast inflation. Procedia Comput Sci 36(12)
Å EstanoviÄ Tea (2019) Jordan neural network for inflation forecasting. Croat Oper Res Rev. 10(7) 23–33
Hurtado C, Luís J, Cortes Fregoso, Hector J (2013) Forecasting mexican inflation using neural networks. In: CONIELECOMP 2013 23rd international conference on electronics, communications and computing. 32–35
Hasan Kiaee (2018) Determinants of inflation in selected countries. 07
Jyh-Shing Roger Jang, Chuen-Tsai Sun, Eiji Mizutani (1997) Neuro-fuzzy and soft computing
Ruzima M (2016) Impact of inflation on economic growth: a survey of literature review. 5(4)
Hadrat Yusif, Eric Effah Sarkodie (2015) Inflation forecasting in the Ghana–artificial neural network model approach. Int J Econ Manag Sci 4(1)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Maldeni, R., Mascrenghe, M.A. (2022). A Machine Learning Approach to CCPI-Based Inflation Prediction. In: Yang, XS., Sherratt, S., Dey, N., Joshi, A. (eds) Proceedings of Sixth International Congress on Information and Communication Technology. Lecture Notes in Networks and Systems, vol 236. Springer, Singapore. https://doi.org/10.1007/978-981-16-2380-6_50
Download citation
DOI: https://doi.org/10.1007/978-981-16-2380-6_50
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-2379-0
Online ISBN: 978-981-16-2380-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)