Macroeconomic indicators alone can predict the monthly closing price of major U.S. indices: Insights from artificial intelligence, time-series analysis and hybrid models

Weng, Bin; Martinez, Waldyn G.; Tsai, Yao-Te; Li, Chen; Lin, Liwu; Barth, James R.; Megahed, Fadel M.

doi:10.1016/j.asoc.2018.07.024

Cited by 33 publications

(18 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, in this paper, the hybrid formulation proposed here, the residuals from the rolling LSTM model are analyzed for further optimization, given its nonparametric nature and nonlinear predictive ability. An improvement on the metrics would suggest that the residuals are not entirely random and validate the conjecture that macroeconomic predictors can further improve the time-series formulation [32,33]. Therefore, this study uses MAPE and RMSE as the judgment prediction capability indicators.…”

Section: Predictive Evaluation Indicatorsmentioning

confidence: 64%

On the Application of ARIMA and LSTM to Predict Order Demand Based on Short Lead Time and On-Time Delivery Requirements

2021

View full text Add to dashboard Cite

Suppliers are adjusting from the order-to-order manufacturing production mode toward demand forecasting. In the meantime, customers have increased demand uncertainty due to their own considerations, such as end-product demand frustration, which leads to suppliers’ inaccurate demand forecasting and inventory wastes. Our research applies ARIMA and LSTM techniques to establish rolling forecast models, which greatly improve accuracy and efficiency of demand and inventory forecasting. The forecast models, developed through historical data, are evaluated and verified by the root mean squares and average absolute error percentages in the actual case application, i.e., the orders of IC trays for semiconductor production plants. The proposed ARIMA and LSTM are superior to the manufacturer’s empirical model prediction results, with LSTM exhibiting enhanced performance in terms of short-term forecasting. The inventory continued to decline significantly after two months of model implementation and application.

show abstract

Section: Predictive Evaluation Indicatorsmentioning

confidence: 64%

On the Application of ARIMA and LSTM to Predict Order Demand Based on Short Lead Time and On-Time Delivery Requirements

2021

View full text Add to dashboard Cite

show abstract

“…The results have demonstrated that the forecasting performances of these ensemble learning methods are superior to traditional time series models. Additionally, this study proposes a hybrid approach of long short term memory, and then, it proves that macroeconomic features are pioneers [11].…”

Section: Literature Reviewmentioning

confidence: 78%

“…Regarding the perspective that macroeconomic indicators can solely predict the accurate one-month ahead price of major US stock indices, four ensemble models of random forest quantile regression, quantile regression neural network, bagging regression and boosting regression have been created by Wong et al [11]. The results have demonstrated that the forecasting performances of these ensemble learning methods are superior to traditional time series models.…”

Section: Literature Reviewmentioning

confidence: 99%

The Predictability of Tree-based Machine Learning Algorithms in the Big Data Context

Qolipour

Ghasemzadeh

Mohammadkarimi

2021

IJE

View full text Add to dashboard Cite

This research work is concerned with the predictability of ensemble and singular tree-based machine learning algorithms during the recession and prosperity of the two companies listed in the Tehran Stock Exchange in the context of big data. In this regard, the main issue is that economic managers and the academic community require predicting models with more accuracy and reduced execution time; moreover, the prediction of the companies recession in the stock market is highly significant. Machine learning algorithms must be able to appropriately predict the stock return sign during the market downturn and boom days. Addressing the stated challenge will upgrade the quality of stock purchases and, subsequently, will increase profitability. In this article, the proposed solution relies on the utilization of tree-based machine learning algorithms in the context of big data. The proposed solution exploits the decision tree algorithm, which is a traditional and singular tree-based learning algorithm. Furthermore, two modern and ensemble tree-based learning algorithms, random forest and gradient boosted tree, has been utilized for predicting the stock return sign during recession and prosperity. The mentioned cases were implemented by applying the machine learning tools in python programming language and PYSPARK library that is used explicitly for the big data context. The utilized research data of the current study are the shares information of two companies of the Tehran Stock Exchange. The obtained results reveal that the applied ensemble learning algorithms have performed better than the singular learning algorithms. Additionally, adding 23 technical features to the initial data and subsequent applying of the PCA feature reduction method have demonstrated the best performance among other modes. In the meantime, it has been concluded that the initial data do not possess the proper resolution or generalizability, either during prosperity or recession.

show abstract

“…Regression methods, including linear, ridge, and lasso used for economic time series forecasting [7, 8], for forecasting financial and macroeconomic variables [9], for corporate failure predicting [10], and so on. The decision tree method is used both individually and in comparison with other techniques: macroeconomic indicators prediction [11], financial credit risk assessment [12], and transit service quality analysis [13]. Support vector machine method realized for credit scoring modeling [14].…”

Section: Literature Reviewmentioning

confidence: 99%

Classical Machine Learning Methods in Economics Research: Macro and Micro Level Examples

Babenko

Panchyshyn

Zomchak

et al. 2021

Wseas Transactions on Business and Economics

View full text Add to dashboard Cite

Paper reviews the classical methods of machine learning (supervised and unsupervised learning),gives examples of the application of different methods and discusses approaches that will be useful for empiricaleconomics research (on data from Ukrainian firms, banks and official state statistics). The different sectors ofeconomics are investigated: the multiple linear regression is used on macrolevel for macro production functionof Ukraine specification; logistic regression is used in bank sector for credit risk management with the scoringmodel; k-means, hierarchic clustering and DBSCAN are used in regional level for regions of Ukraine groupingbased on competitiveness; principal component analysis is used for firm’s financial stability analysis. All modelsshowed adequate simulation results according to the quality criteria of the models. So, the possibility ofclassic machine learning methods application for investigations of the processes and objects on different levelsof economics (micro, mezzo and macro) is demonstrated in the article.

show abstract

Macroeconomic indicators alone can predict the monthly closing price of major U.S. indices: Insights from artificial intelligence, time-series analysis and hybrid models

Cited by 33 publications

References 56 publications

On the Application of ARIMA and LSTM to Predict Order Demand Based on Short Lead Time and On-Time Delivery Requirements

On the Application of ARIMA and LSTM to Predict Order Demand Based on Short Lead Time and On-Time Delivery Requirements

The Predictability of Tree-based Machine Learning Algorithms in the Big Data Context

Classical Machine Learning Methods in Economics Research: Macro and Micro Level Examples

Contact Info

Product

Resources

About