A Fusion Framework for Forecasting Financial Market Direction Using Enhanced Ensemble Models and Technical Indicators

People continuously hunt for a precise and productive strategy to control the stock exchange because the monetary trade is recognised for its unbelievably different character and unpredictability. Even a minor gain in predicting performance will be extremely profitable and significant. Our novel stu...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Dushmanta Kumar Padhi, Neelamadhab Padhy, Akash Kumar Bhoi, Jana Shafi, Muhammad Fazal Ijaz
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	stock exchange stock market ensemble cross-validation LDA hist gradient boosting Mathematics QA1-939
Acceso en línea:	https://doaj.org/article/50df52bfacf34d68becae374d9393c37
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:50df52bfacf34d68becae374d9393c37
record_format	dspace
spelling	oai:doaj.org-article:50df52bfacf34d68becae374d9393c372021-11-11T18:13:34ZA Fusion Framework for Forecasting Financial Market Direction Using Enhanced Ensemble Models and Technical Indicators10.3390/math92126462227-7390https://doaj.org/article/50df52bfacf34d68becae374d9393c372021-10-01T00:00:00Zhttps://www.mdpi.com/2227-7390/9/21/2646https://doaj.org/toc/2227-7390People continuously hunt for a precise and productive strategy to control the stock exchange because the monetary trade is recognised for its unbelievably different character and unpredictability. Even a minor gain in predicting performance will be extremely profitable and significant. Our novel study implemented six boosting techniques, i.e., XGBoost, AdaBoost, Gradient Boosting, LightGBM, CatBoost, and Histogram-based Gradient Boosting, and these boosting techniques were hybridised using a stacking framework to find out the direction of the stock market. Five different stock datasets were selected from four different countries and were used for our experiment. We used two-way overfitting protection during our model building process, i.e., dynamic reduction technique and cross-validation technique. For model evaluation purposes, we used the performance metrics, i.e., accuracy, ROC curve (AUC), F-score, precision, and recall. The aim of our study was to propose and select a predictive model whose training and testing accuracy difference was minimal in all stocks. The findings revealed that the meta-classifier Meta-LightGBM had training and testing accuracy differences that were very low among all stocks. As a result, a proper model selection might allow investors the freedom to invest in a certain stock in order to successfully control risk and create short-term, sustainable profits.Dushmanta Kumar PadhiNeelamadhab PadhyAkash Kumar BhoiJana ShafiMuhammad Fazal IjazMDPI AGarticlestock exchangestock marketensemblecross-validationLDAhist gradient boostingMathematicsQA1-939ENMathematics, Vol 9, Iss 2646, p 2646 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	stock exchange stock market ensemble cross-validation LDA hist gradient boosting Mathematics QA1-939
spellingShingle	stock exchange stock market ensemble cross-validation LDA hist gradient boosting Mathematics QA1-939 Dushmanta Kumar Padhi Neelamadhab Padhy Akash Kumar Bhoi Jana Shafi Muhammad Fazal Ijaz A Fusion Framework for Forecasting Financial Market Direction Using Enhanced Ensemble Models and Technical Indicators
description	People continuously hunt for a precise and productive strategy to control the stock exchange because the monetary trade is recognised for its unbelievably different character and unpredictability. Even a minor gain in predicting performance will be extremely profitable and significant. Our novel study implemented six boosting techniques, i.e., XGBoost, AdaBoost, Gradient Boosting, LightGBM, CatBoost, and Histogram-based Gradient Boosting, and these boosting techniques were hybridised using a stacking framework to find out the direction of the stock market. Five different stock datasets were selected from four different countries and were used for our experiment. We used two-way overfitting protection during our model building process, i.e., dynamic reduction technique and cross-validation technique. For model evaluation purposes, we used the performance metrics, i.e., accuracy, ROC curve (AUC), F-score, precision, and recall. The aim of our study was to propose and select a predictive model whose training and testing accuracy difference was minimal in all stocks. The findings revealed that the meta-classifier Meta-LightGBM had training and testing accuracy differences that were very low among all stocks. As a result, a proper model selection might allow investors the freedom to invest in a certain stock in order to successfully control risk and create short-term, sustainable profits.
format	article
author	Dushmanta Kumar Padhi Neelamadhab Padhy Akash Kumar Bhoi Jana Shafi Muhammad Fazal Ijaz
author_facet	Dushmanta Kumar Padhi Neelamadhab Padhy Akash Kumar Bhoi Jana Shafi Muhammad Fazal Ijaz
author_sort	Dushmanta Kumar Padhi
title	A Fusion Framework for Forecasting Financial Market Direction Using Enhanced Ensemble Models and Technical Indicators
title_short	A Fusion Framework for Forecasting Financial Market Direction Using Enhanced Ensemble Models and Technical Indicators
title_full	A Fusion Framework for Forecasting Financial Market Direction Using Enhanced Ensemble Models and Technical Indicators
title_fullStr	A Fusion Framework for Forecasting Financial Market Direction Using Enhanced Ensemble Models and Technical Indicators
title_full_unstemmed	A Fusion Framework for Forecasting Financial Market Direction Using Enhanced Ensemble Models and Technical Indicators
title_sort	fusion framework for forecasting financial market direction using enhanced ensemble models and technical indicators
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/50df52bfacf34d68becae374d9393c37
work_keys_str_mv	AT dushmantakumarpadhi afusionframeworkforforecastingfinancialmarketdirectionusingenhancedensemblemodelsandtechnicalindicators AT neelamadhabpadhy afusionframeworkforforecastingfinancialmarketdirectionusingenhancedensemblemodelsandtechnicalindicators AT akashkumarbhoi afusionframeworkforforecastingfinancialmarketdirectionusingenhancedensemblemodelsandtechnicalindicators AT janashafi afusionframeworkforforecastingfinancialmarketdirectionusingenhancedensemblemodelsandtechnicalindicators AT muhammadfazalijaz afusionframeworkforforecastingfinancialmarketdirectionusingenhancedensemblemodelsandtechnicalindicators AT dushmantakumarpadhi fusionframeworkforforecastingfinancialmarketdirectionusingenhancedensemblemodelsandtechnicalindicators AT neelamadhabpadhy fusionframeworkforforecastingfinancialmarketdirectionusingenhancedensemblemodelsandtechnicalindicators AT akashkumarbhoi fusionframeworkforforecastingfinancialmarketdirectionusingenhancedensemblemodelsandtechnicalindicators AT janashafi fusionframeworkforforecastingfinancialmarketdirectionusingenhancedensemblemodelsandtechnicalindicators AT muhammadfazalijaz fusionframeworkforforecastingfinancialmarketdirectionusingenhancedensemblemodelsandtechnicalindicators
_version_	1718431882942611456

A Fusion Framework for Forecasting Financial Market Direction Using Enhanced Ensemble Models and Technical Indicators

Ejemplares similares