Explainable inflation forecasts by machine learning models

Aras, Serkan; Lisboa, Paulo J. G.

doi:10.1016/j.eswa.2022.117982

Cited by 13 publications

(6 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is shown that core inflation estimated by the synthesis of multiple indicators has a stronger capacity of capturing economic event as well as responding to monetary policy than the counterpart estimated by the single-indicator filtering method. Using machine learning model and Shapley decomposition, Aras and Lisboa (2022) states that machine learning will improve the estimation accuracy of core inflation system significantly. Although these studies have made great contributions to core inflation measurement, their applications will be subject to some rigorous constraints.…”

Section: Literature Reviewmentioning

confidence: 99%

“…This is in contrast to the inflation pattern of many economies (e.g., the US and Europe). Bermingham (2010), Aras and Lisboa (2022) and Kim and Lim (2022) propose that as the US, South Korea and most other developed economies have entered the high-income stage, the proportion of food consumption in total consumption is relatively small, thus core inflation trend is less influenced by the food category. As a result, most studies choose to target core inflation trend for inflation regulation and expectation management.…”

Section: Sectoral Core Inflation Decomposition and Contribution Measu...mentioning

confidence: 99%

See 1 more Smart Citation

Solving the Puzzle of China’s Low Inflation: A New Perspective From Sectoral Core Inflation Fluctuations

Liu,

Xu,

Song

et al. 2024

Technological and Economic Development of Economy

View full text Add to dashboard Cite

China’s constantly rapid economic growth accompanying by a low overall inflation has long been mysterious in macroeconomics. The core purpose of this paper is to solve this puzzle. Therefore, we integrate overdetermined set of equations into a MUCSVO model to explore the volatility mechanism of the overall inflation from a sectoral perspective. Our key findings include: 1) the hedging effect of sectoral inflation fluctuations principally accounts for China’s long-run stable overall inflation; 2) the main contradiction of China’s inflation has been shifting from high price levels in the traditional food and residence categories to rising prices in the health care category; 3) as the proportions of inflation in the food and residence categories fall steadily, sectoral inflation weights become more evenly distributed. In conclusion, China’s overall inflation and deflation will be much less likely to occur, while inflation is still of sectoral imbalance. Unusual price fluctuations in the food and health care categories, which are highly relevant to basic living standards of the low-income group, deserve close attention in particular. Overall, besides solving the puzzle of China’s low inflation, our model is applicable to economies that do not publish inflation weights, which is a useful extension of core inflation measurement.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Sectoral Core Inflation Decomposition and Contribution Measu...mentioning

confidence: 99%

Solving the Puzzle of China’s Low Inflation: A New Perspective From Sectoral Core Inflation Fluctuations

Liu,

Xu,

Song

et al. 2024

Technological and Economic Development of Economy

View full text Add to dashboard Cite

show abstract

“…In presenting their results, they found that deep learning models provide more accurate predictions than traditional statistical methods. Aras and Lisboa (2022) investigated the applicability of machine learning methods for forecasting inflation in Turkey. Turkish inflation was high during the period they analysed and showed a high volatility.…”

Section: Inflation Forecastmentioning

confidence: 99%

“…Most of the research focuses on the forecasting of financial markets (Liu et al 2021;Ayala et al 2021;Bhandari et al 2022;Hanauer and Kalsbach 2023;Md et al 2023;). Among the publications dealing with macro data, the topic of inflation is quite popular (Ülke et al 2018;Medeiros et al 2021;Joseph et al 2021;Aras and Lisboa 2022;Araujo and Gaglianone 2023). It is a restricted group of studies where researchers analyse inflation data and stock markets combined.…”

Section: Protection Against Inflation Through Portfolio Re-allocationmentioning

confidence: 99%

Navigating Inflation Challenges: AI-Based Portfolio Management Insights

Bareith,

Tatay,

Vancsura

2024

Risks

View full text Add to dashboard Cite

After 2010, the consumer price index fell to a low level in the EU. In the euro area, it remained low between 2010 and 2020. The European Central Bank has even had to take action against the emergence of deflation. The situation changed significantly in 2021. Inflation jumped to levels not seen for 40 years in the EU. Our study aims to use artificial intelligence to forecast inflation. We also use artificial intelligence to forecast stock index changes. Based on the forecasts, we propose portfolio reallocation decisions to protect against inflation. The forecasting literature does not address the importance of structural breaks in the time series, which, among other things, can affect both the pattern recognition and prediction capabilities of various machine learning models. The novelty of our study is that we used the Zivot–Andrews unit root test to determine the breakpoints and partitioned the time series into training and testing datasets along these points. We then examined which database partition gives the most accurate prediction. This information can be used to re-balance the portfolio. Two different AI-based prediction algorithms were used (GRU and LSTM), and a hybrid model (LSTM–GRU) was also included to investigate the predictability of inflation. Our results suggest that the average error of the inflation forecast is a quarter of that of the stock market index forecast. Inflation developments have a fundamental impact on equity and government bond returns. If we obtain a reliable estimate of the inflation forecast, we have time to rebalance the portfolio until the inflation shock is incorporated into government bond returns. Our results not only support investment decisions at the national economy level but are also useful in the process of rebalancing international portfolios.

show abstract

“…Medeiros et al (2019) demonstrate in a pre-pandemic sample how random forest models in particular, consistently outperform conventional univariate models (e.g., Stock & Watson, 2010) in forecasting US inflation. Similarly, Aras and Lisboa (2022) show the efficacy of tree-based modeling, on their own and in conjunction with standard econometric models, in forecasting volatile inflation rates in Turkey. Vrontos et al (2021) reach similarly favorable results using logit, k-nearest neighbors, and Bayesian generalized linear models to predict US recessions.…”

Section: Introductionmentioning

confidence: 99%

Using deep (machine) learning to forecast US inflation in the COVID‐19 era

Stoneman,

Duca

2024

Journal of Forecasting

View full text Add to dashboard Cite

The 2021–2022 surge in US inflation was unanticipated by the Survey of Professional Forecasters (SPF) and other macroeconomists and institutions. This study assesses whether nascent deep learning frameworks and methods more accurately project recent core personal consumption expenditures inflation. We create a recurrent neural network (RNN) to forecast long‐term inflation, and after training on 60 years of quarterly data, the model outperforms the SPF and projects a spike in inflation similar to that of recent years. We compare the model's performance with and without COVID‐19–specific data and discuss some implications of our findings for economic forecasting in global crises.

show abstract

Explainable inflation forecasts by machine learning models

Cited by 13 publications

References 67 publications

Solving the Puzzle of China’s Low Inflation: A New Perspective From Sectoral Core Inflation Fluctuations

Solving the Puzzle of China’s Low Inflation: A New Perspective From Sectoral Core Inflation Fluctuations

Navigating Inflation Challenges: AI-Based Portfolio Management Insights

Using deep (machine) learning to forecast US inflation in the COVID‐19 era

Contact Info

Product

Resources

About