A Regression Based Approach To Predict The Indian Stock Market Trend Amid COVID-19

Rouf, Nusrat; Malik, Majid Bashir; Arif, Tasleem

doi:10.1109/icac3n53548.2021.9725396

Cited by 3 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As seen from the previous works, technical indicators play a significant role in predicting the markets [ 50 ]. Also, COVID-19 has significantly affected the financial markets [ 7 ]. In our approach, an attempt has been made to predict the Nifty50 index prices using basic market data COVID-19 data and derived technical indicators.…”

Section: Methodsmentioning

confidence: 99%

“…# Using Ridge (12) SET ridge TO Ridge(alpha TO 7) ridge.fit(X,Y) (13) SET ranks["Ridge"] TO ranking(np.abs(ridge.coef_), colnames) # Using Lasso (14) SET lasso TO Lasso(alpha � 0.05) lasso.fit(X, Y) (15) SET ranks["Lasso"] TO ranking(np.abs(lasso.coef_), colnames) # Using Random Forest #Sort the dataframe (28) SET meanplot TO meanplot.sort_values("Mean Ranking," ascending � False) #Plot the ranking of the features (29) SET sns.factorplot(x � "Mean Ranking," y � "Feature," data TO meanplot, kind � "bar," size � 14, aspect � 1.9, palette � "coolwarm") ALGORITHM 1: Hybrid feature selection mechanism.…”

Section: Prediction Approachmentioning

confidence: 99%

“…Global markets have labelled this disaster a black swan event. This pandemic has significantly disturbed and influenced stock market activity around the world [ 7 ]. In year 2020, due to the effects of pandemic, it was estimated that the China's Gross Domestic Product (GDP) may fall by 6.2 percent, while the United States (US) GDP may plunge down by 8.4 percent [ 2 , 8 ].…”

Section: Introductionmentioning

confidence: 99%

“…Artificial Neural Network (ANN) models are the most popular method that adapt to the dynamic nature of markets easily [ 12 ]. These are the models that understand the context of a problem by creating multiple linear transformations on the feature space followed by a nonlinearity to create its simplified representation [ 7 , 13 ]. Neural network models can represent any distribution over the input feature space; therefore, they are known as universal function approximator [ 14 ].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Impact of Healthcare on Stock Market Volatility and Its Predictive Solution Using Improved Neural Network

Rouf

Malik

Sharma

et al. 2022

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

The unprecedented Corona Virus Disease (COVID-19) pandemic has put the world in peril and shifted global landscape in unanticipated ways. The SARSCoV2 virus, which caused the COVID-19 outbreak, first appeared in Wuhan, Hubei Province, China, in December 2019 and quickly spread around the world. This pandemic is not only a global health crisis, but it has caused the major global economic depression. As soon as the virus spread, stock market prices plummeted and volatility increased. Predicting the market during this outbreak has been of substantial importance and is the primary motivation to carry out this work. Given the nonlinearity and dynamic nature of stock data, the prediction of stock market is a challenging task. The machine learning models have proven to be a good choice for the development of effective and efficient prediction systems. In recent years, the application of hyperparameter optimization techniques for the development of highly accurate models has increased significantly. In this study, a customized neural network model is proposed and the power of hyperparameter optimization in modelling stock index prices is explored. A novel dataset is generated using nine standard technical indicators and COVID-19 data. In addition, the primary focus is on the importance of selection of optimal features and their preprocessing. The utilization of multiple feature ranking techniques combined with extensive hyperparameter optimization procedures is comprehensive for the prediction of stock index prices. Moreover, the model is evaluated by comparing it with other models, and results indicate that the proposed model outperforms other models. Given the detailed design methodology, preprocessing, exploratory feature analysis, and hyperparameter optimization procedures, this work gives a significant contribution to stock analysis research community during this pandemic.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Prediction Approachmentioning

confidence: 99%