An Interpretable Machine Learning Approach in Predicting Inflation Using Payments System Data: A Case Study of Indonesia

TL;DR

This study demonstrates that machine learning models, especially Extreme Gradient Boosting, outperform traditional ARIMA models in predicting Indonesia's inflation using payment system data, offering interpretable insights for monetary policy.

Contribution

The paper introduces the application of ML models with interpretability techniques like Shapley values to inflation prediction, surpassing traditional econometric models in accuracy and insight.

Findings

ML models reduce forecast errors by 45.16% compared to ARIMA.

Extreme Gradient Boosting outperforms other ML models.

Payment system variables significantly influence inflation predictions.

Abstract

This paper evaluates the performance of prominent machine learning (ML) algorithms in predicting Indonesia's inflation using the payment system, capital market, and macroeconomic data. We compare the forecasting performance of each ML model, namely shrinkage regression, ensemble learning, and super vector regression, to that of the univariate time series ARIMA and SARIMA models. We examine various out-of-bag sample periods in each ML model to determine the appropriate data-splitting ratios for the regression case study. This study indicates that all ML models produced lower RMSEs and reduced average forecast errors by 45.16 percent relative to the ARIMA benchmark, with the Extreme Gradient Boosting model outperforming other ML models and the benchmark. Using the Shapley value, we discovered that numerous payment system variables significantly predict inflation. We explore the ML forecast using local Shapley decomposition and show the relationship between the explanatory variables and inflation for interpretation. The interpretation of the ML forecast highlights some significant findings and offers insightful recommendations, enhancing previous economic research that uses a more established econometric method. Our findings advocate ML models as supplementary tools for the central bank to predict inflation and support monetary policy.