FEB-Stacking and FEB-DNN Models for Stock Trend Prediction: A Performance Analysis for Pre and Post Covid-19 Periods
In this paper, stock price prediction is perceived as a binary classification problem where the goal is to predict whether an increase or decrease in closing prices is going to be observed the next day. The framework will be of use for both investors and traders. In the aftermath of the Covid-19 pan...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Regional Association for Security and crisis management
2021-02-01
|
| Series: | Decision Making: Applications in Management and Engineering |
| Subjects: | |
| Online Access: | https://dmame.rabek.org/index.php/dmame/article/view/163 |
| _version_ | 1818461421785055232 |
|---|---|
| author | Indranil Ghosh Tamal Datta Chaudhuri |
| author_facet | Indranil Ghosh Tamal Datta Chaudhuri |
| author_sort | Indranil Ghosh |
| collection | DOAJ |
| description | In this paper, stock price prediction is perceived as a binary classification problem where the goal is to predict whether an increase or decrease in closing prices is going to be observed the next day. The framework will be of use for both investors and traders. In the aftermath of the Covid-19 pandemic, global financial markets have seen growing uncertainty and volatility and as a consequence, precise prediction of stock price trend has emerged to be extremely challenging. In this background, we propose two integrated frameworks wherein rigorous feature engineering, methodology to sort out class imbalance, and predictive modeling are clubbed together to perform stock trend prediction during normal and new normal times. A number of technical and macroeconomic indicators are chosen as explanatory variables, which are further refined through dedicated feature engineering process by applying Kernel Principal Component (KPCA) analysis. Bootstrapping procedure has been used to deal with class imbalance. Finally, two separate Artificial Intelligence models namely, Stacking and Deep Neural Network models are deployed separately on feature engineered and bootstrapped samples for estimating trends in prices of underlying stocks during pre and post Covid-19 periods. Rigorous performance analysis and comparative evaluation with other well-known models justify the effectiveness and superiority of proposed frameworks. |
| first_indexed | 2024-12-14T23:45:53Z |
| format | Article |
| id | doaj.art-d00e01380b414bd9b1b432445eca1927 |
| institution | Directory Open Access Journal |
| issn | 2560-6018 2620-0104 |
| language | English |
| last_indexed | 2024-12-14T23:45:53Z |
| publishDate | 2021-02-01 |
| publisher | Regional Association for Security and crisis management |
| record_format | Article |
| series | Decision Making: Applications in Management and Engineering |
| spelling | doaj.art-d00e01380b414bd9b1b432445eca19272022-12-21T22:43:24ZengRegional Association for Security and crisis managementDecision Making: Applications in Management and Engineering2560-60182620-01042021-02-0141518410.31181/dmame2104051g163FEB-Stacking and FEB-DNN Models for Stock Trend Prediction: A Performance Analysis for Pre and Post Covid-19 PeriodsIndranil Ghosh0Tamal Datta Chaudhuri1Calcutta Business School, West Bengal, India Calcutta Business School, West Bengal, India In this paper, stock price prediction is perceived as a binary classification problem where the goal is to predict whether an increase or decrease in closing prices is going to be observed the next day. The framework will be of use for both investors and traders. In the aftermath of the Covid-19 pandemic, global financial markets have seen growing uncertainty and volatility and as a consequence, precise prediction of stock price trend has emerged to be extremely challenging. In this background, we propose two integrated frameworks wherein rigorous feature engineering, methodology to sort out class imbalance, and predictive modeling are clubbed together to perform stock trend prediction during normal and new normal times. A number of technical and macroeconomic indicators are chosen as explanatory variables, which are further refined through dedicated feature engineering process by applying Kernel Principal Component (KPCA) analysis. Bootstrapping procedure has been used to deal with class imbalance. Finally, two separate Artificial Intelligence models namely, Stacking and Deep Neural Network models are deployed separately on feature engineered and bootstrapped samples for estimating trends in prices of underlying stocks during pre and post Covid-19 periods. Rigorous performance analysis and comparative evaluation with other well-known models justify the effectiveness and superiority of proposed frameworks.https://dmame.rabek.org/index.php/dmame/article/view/163binary classificationkernel principal component (kpca)bootstrappingstackingdeep neural network |
| spellingShingle | Indranil Ghosh Tamal Datta Chaudhuri FEB-Stacking and FEB-DNN Models for Stock Trend Prediction: A Performance Analysis for Pre and Post Covid-19 Periods Decision Making: Applications in Management and Engineering binary classification kernel principal component (kpca) bootstrapping stacking deep neural network |
| title | FEB-Stacking and FEB-DNN Models for Stock Trend Prediction: A Performance Analysis for Pre and Post Covid-19 Periods |
| title_full | FEB-Stacking and FEB-DNN Models for Stock Trend Prediction: A Performance Analysis for Pre and Post Covid-19 Periods |
| title_fullStr | FEB-Stacking and FEB-DNN Models for Stock Trend Prediction: A Performance Analysis for Pre and Post Covid-19 Periods |
| title_full_unstemmed | FEB-Stacking and FEB-DNN Models for Stock Trend Prediction: A Performance Analysis for Pre and Post Covid-19 Periods |
| title_short | FEB-Stacking and FEB-DNN Models for Stock Trend Prediction: A Performance Analysis for Pre and Post Covid-19 Periods |
| title_sort | feb stacking and feb dnn models for stock trend prediction a performance analysis for pre and post covid 19 periods |
| topic | binary classification kernel principal component (kpca) bootstrapping stacking deep neural network |
| url | https://dmame.rabek.org/index.php/dmame/article/view/163 |
| work_keys_str_mv | AT indranilghosh febstackingandfebdnnmodelsforstocktrendpredictionaperformanceanalysisforpreandpostcovid19periods AT tamaldattachaudhuri febstackingandfebdnnmodelsforstocktrendpredictionaperformanceanalysisforpreandpostcovid19periods |