A comparison of time series and machine learning models for inflation forecasting: empirical evidence from the USA

Ülke, Volkan; Şahin, Afşin; Subaşı, Abdülhamit

doi:10.1007/s00521-016-2766-x

Cited by 35 publications

(14 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These findings support our modeling strategy when neural networks are considered in practical applications, i.e., for forecasting purposes. This is in line with [18,38] who found that multivariate models and more variables can improve inflation forecasts, while it is opposite to findings of [24,28] favoring simpler models. The same conclusion emerges when JNNs are compared with appropriate ARIMA models.…”

Section: Empirical Results and Discussionsupporting

confidence: 79%

“…Most previous studies have focused on inflation forecasting using ARIMA, STAR and VAR models, see, e.g., [7,[12][13][14]. Some of the studies have compared traditional econometric models against neural networks when forecasting inflation, see, e.g., [15][16][17][18], but only a few of them have dealt with the recurrent neural network as the competing one among other neural network structures, see, e.g., [10,19,20].…”

Section: Previous Studiesmentioning

confidence: 99%

“…[10] showed that JNN has a significantly better forecasting performance one and six months ahead compared to the FNN. On the other hand, [18] compared machine learning models, including FNNs, with standard time-series models and concluded that multivariate models produce the most precise results in all horizons and that there is no single best model to forecast inflation. Namely, NN-type models may be applied to the CPI inflation forecasting, while the ARDL model is a better option for other inflation measures.…”

Section: Previous Studiesmentioning

confidence: 99%

See 2 more Smart Citations

Can Recurrent Neural Networks Predict Inflation in Euro Zone as Good as Professional Forecasters?

Šestanović

Arnerić

2021

Mathematics

View full text Add to dashboard Cite

This paper investigates whether a specific type of a recurrent neural network, in particular Jordan neural network (JNN), captures the expected inflation better than commonly used feedforward neural networks and traditional parametric time-series models. It also considers competing survey-based and model-based expected inflation towards ex-post actual inflation to find whose predictions are more accurate; predictions from survey respondents or forecasting modelers. Further, it proposes neural network modelling strategy when dealing with nonstationary time-series which exhibit long-memory property and nonlinear dependence with respect to lagged inputs and exogenous inputs as well. Following this strategy, overfitting problem was reduced until no improvement in forecasting accuracy of expected inflation is achieved. The main finding is that JNN predicts inflation in euro zone quite accurately within forecasting horizon of 2 years. Regarding rational expectation principle we have found a set of demand-pull and cost-push inflation characteristics as exogenous inputs which helps in reducing overfitting problem of recurrent neural network even more. The sample includes euro zone aggregated monthly observations from January 2000 to December 2019. The results also confirm that inflation expectations obtained from JNN are consistent with Survey of professional forecasters (SPF), and thus, monetary policy makers can use JNN as a complementary tool in shortcomings of other inflation expectations measures.

show abstract

Section: Empirical Results and Discussionsupporting

confidence: 79%

Section: Previous Studiesmentioning

confidence: 99%

Section: Previous Studiesmentioning

confidence: 99%

See 1 more Smart Citation

Can Recurrent Neural Networks Predict Inflation in Euro Zone as Good as Professional Forecasters?

Šestanović

Arnerić

2021

Mathematics

View full text Add to dashboard Cite

show abstract

“…Finally, to provide a comparison with the adopted time series-forecasting model's performance, the model is compared to benchmark forecasting models. This is done to determine if an adopted forecasting model provides significant improvement to "simply using today's value in predicting tomorrow's value" (Hyndman & Koehler, 2006;Ülke, Sahin, & Subasi, 2018).…”

Section: Case Studymentioning

confidence: 99%

A Seasonal Autoregressive Integrated Moving Average (SARIMA) Model to Forecasting Tourist Arrival in the Philippines: A Case Study in Moalboal, Cebu (Philippines)

Velos

Bate

et al. 2020

RMRJ

View full text Add to dashboard Cite

Forecasting plays a critical part in implementing effective tourism management strategies. However, the role of tourism forecasting is not extensively studied in the Philippines, which is a key tourism destination in Southeast Asia. To address such gap, this paper explores the dynamics of tourist demand in the Philippines through a case study. It illustrates the tourist arrival using a SARIMA model. Results show that the adopted methodology was able to capture the dynamics of the tourist demand in the Philippines. By providing lenses to the Philippine tourism case, this paper would help shed light to the gaps in the literature's current understanding of tourism in the Philippines. Moreover, these findings would be beneficial for stakeholders in shaping policies, strategies, and other tourism initiatives.

show abstract

“…The historical information created by stock exchanges is gigantic. Since the measure of information to be examined is so immense, it is extremely hard for any person to consider every one of the information esteems while anticipating future stock trends [1]. The basic and specialized investigations are two principle systems pervasive in money that is utilized for financial exchange expectations.…”

Section: Introductionmentioning

confidence: 99%

Summarize the Work Related to Prediction of Stock Market’s Option Prices with Artificial Intelligence using Standard Dataset

Pathak*,

Kumar

2019

IJRTE

View full text Add to dashboard Cite

Forecasting and prediction are based on pattern recognition. It may be a human energy potential increase day today when he grownup a young guy, but afterward, his energy potential going downwards. So, we observed the pattern with the help of neural network models; these are radical bias function (RBP) and back-propagation (BP). Utilizing the neural network model, it also has many classification parts like a deep neural network, feedforward neural network, recurrent neural network, convolutional neural network and many more. In the forecasting or prediction, we have a large amount of data to manage. We trained the data with algorithm and here we also use the neural network models. We used optimization techniques that are inspired by biological swarm. Nowadays, lots of data generate day by day like market, medical, education, automobile, etc. we need recognition of the pattern for prediction of future expectations. That expectation of prediction very helpful and needy to gain profit of human beings. In this work, we use SOM (self-Organized Map), RBF (Radical Bias Function), DNN (Deep Neural Network) and PGO (Plant Grow Optimization). The total data point for the processing used 27500. The evaluation of the performance used standard parameters such as ET, MAE, MSE, RMSE and MI. The proposed algorithm implemented in MATLAB software. The cascaded neural network classifier is the combination of the SOM and RBF neural network models. The SOM neural network model proceeds the task of clustering and RBF neural network model used for prediction.

show abstract

A comparison of time series and machine learning models for inflation forecasting: empirical evidence from the USA

Cited by 35 publications

References 40 publications

Can Recurrent Neural Networks Predict Inflation in Euro Zone as Good as Professional Forecasters?

Can Recurrent Neural Networks Predict Inflation in Euro Zone as Good as Professional Forecasters?

A Seasonal Autoregressive Integrated Moving Average (SARIMA) Model to Forecasting Tourist Arrival in the Philippines: A Case Study in Moalboal, Cebu (Philippines)

Summarize the Work Related to Prediction of Stock Market’s Option Prices with Artificial Intelligence using Standard Dataset

Contact Info

Product

Resources

About