Measurement of Economic Forecast Accuracy: A Systematic Overview of the Empirical Literature

Buturac, Goran

doi:10.3390/jrfm15010001

Cited by 7 publications

(5 citation statements)

References 133 publications

(313 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RMSE is useful as a relative measure to compare forecasts for the same series across different models. The MAE and the MdAE are less sensitive to large deviations than the usual squared loss (Buturac, 2022). Lower values of the first three measures indicate higher forecast accuracy.…”

Section: Forecasting Criteriamentioning

confidence: 99%

Robust approach to earnings forecast: A comparison

Yu,

Zhang,

Lien

2024

Journal of Forecasting

View full text Add to dashboard Cite

This paper applies three robust approaches, namely, the MM estimation, the Theil–Sen estimation, and the quantile regression, to generate earnings forecasts in Chinese financial market and evaluates the forecast accuracy of these three methods based on three forecasting criteria. We examine six forecasting models where the predicted variables include earnings per share, net income, and three profitability measures. We show that the three robust methods significantly outperform the OLS method. Moreover, the MM estimation and the quantile regression have better forecast accuracy than the Theil–Sen approach.

show abstract

Section: Forecasting Criteriamentioning

confidence: 99%

Robust approach to earnings forecast: A comparison

Yu,

Zhang,

Lien

2024

Journal of Forecasting

View full text Add to dashboard Cite

show abstract

“…It exists a broad literature concerning the validation of computer models ranging from general discussion of different statistical tests methods [15,16] over the assesment of the general forecast possibilities in particular domains [17] to finetuning of specific tests in certain domains, for example ecological modelling [18].…”

Section: Model Validationmentioning

confidence: 99%

Comprehensive Validation Metrics and Precise Updating of Digital Twins of Production Systems

Overbeck¹,

Louarn²,

Brützel³

et al. 2022

SNE

View full text Add to dashboard Cite

Despite continuous improvements in modelling, software tools and data availability, simulation projects of production systems still require a lot of manual effort, expertise in various disciplines and time. In many projects the high initial invest for building the simulation model is followed by a rather short period of experimentation and analysis. As production systems have to be adapted at an increasing pace to respond to rapidly changing markets and business environments, simulation models of these systems become outdated earlier, reducing their useful time window. One way to extend this time window would be the implementation of a method of automated comparison with the current production systems and subsequent self-adaption of the model to reality to maintain and even improve its accuracy over time. This approach will be presented and validated at a real world use case. Such an enhanced simulation model can be called a digital twin of the production system.

show abstract

“…Over time, institutional investors preferred adopting financial econometric models to analyse financial data and study market features ( Buturac, 2021 ; Datta et al, 2021 ; Messeni Petruzzelli, Murgia & Parmentola, 2021 ). The analysis results of the econometric model are often explanatory.…”

Section: Literature Reviewmentioning

confidence: 99%

Empirical mode decomposition using deep learning model for financial market forecasting

Jin

Jin²,

Chen

2022

PeerJ Computer Science

View full text Add to dashboard Cite

Financial market forecasting is an essential component of financial systems; however, predicting financial market trends is a challenging job due to noisy and non-stationary information. Deep learning is renowned for bringing out excellent abstract features from the huge volume of raw data without depending on prior knowledge, which is potentially fascinating in forecasting financial transactions. This article aims to propose a deep learning model that autonomously mines the statistical rules of data and guides the financial market transactions based on empirical mode decomposition (EMD) with back-propagation neural networks (BPNN). Through the characteristic time scale of data, the intrinsic wave pattern was obtained and then decomposed. Financial market transaction data were analyzed, optimized using PSO, and predicted. Combining the nonlinear and non-stationary financial time series can improve prediction accuracy. The predictive model of deep learning, based on the analysis of the massive financial trading data, can forecast the future trend of financial market price, forming a trading signal when particular confidence is satisfied. The empirical results show that the EMD-based deep learning model has an excellent predicting performance.

show abstract

Measurement of Economic Forecast Accuracy: A Systematic Overview of the Empirical Literature

Cited by 7 publications

References 133 publications

Robust approach to earnings forecast: A comparison

Robust approach to earnings forecast: A comparison

Comprehensive Validation Metrics and Precise Updating of Digital Twins of Production Systems

Empirical mode decomposition using deep learning model for financial market forecasting

Contact Info

Product

Resources

About