Open Access Open Access  Restricted Access Subscription Access

Machine Learning and Deep Learning based Approaches to Predict Nifty Index


Affiliations
1 Associate Professor, Department of Management Studies, Kongu Engineering College, Perundurai, Erode, Tamil Nadu, India
2 II MBA, Department of Management Studies, Kongu Engineering College, Perundurai, Erode, Tamil Nadu, India
 

Stock price prediction is one of the most difficult machine learning issues to solve. The stock market, often known as the equity market, has a significant impact on today's economy. This study discusses about different machine learning and deep learning approaches to predict and evaluate stock prices. Time series data is used to depict stock values and algorithms are trained to learn patterns from trends. For the machine learning approaches, study used linear regression, logistic regression and decision tree and for deep learning approaches Long Short-Term Memory (LSTM) and Recurrent Neural Network (RNN) are used to predict Nifty Index value. These variants are commonly used to forecast stock prices and movements. The algorithm is based on the concept of probability and it is used for predictive analysis. For continuous quantitative data, a regression tree is utilized. Linear Regression, Logistic Regression, Decision Tree, LSTM and RNN are the most noticeable techniques used in financial time series forecasting. The study observed from Python software, that the Linear and Logistic Regression model predicts accuracy of roughly 52% and provides an acceptable return ratio. As a result, study found that the Nifty-50 data set has been utilized to improve the precision of supervised learning and future prediction.

Keywords

Decision Tree, Deep Learning, Linear Regression, Logistic Regression and Nifty
User
Notifications
Font Size

  • Kaya MIY, Karsligil ME. 2nd IEEE International Conference on Information and Financial Engineering (ICIFE). 2010; 478–482.
  • Tsai, Wang S. Stock Price Forecasting by Hybrid Machine Learning Techniques. Proceedings of the International Multi Conference of Engineers and Computer Scientists. 2009.
  • Zhang X, Fuehres H, Gloor PA. Predicting Stock Market Indicators through Twitter “I hope it is not as bad as I fear”. Procedia-Social and Behavioral Sciences. 2011; 55-62. https://doi.org/10.1016/j.sbspro.2011.10.562
  • Nikfarjam A, Emadzadeh E, Muthaiyah S. Text Mining Approaches for Stock Market Prediction. The 2nd International Conference on Computer and Automation Engineering (ICCAE). 2010; 4:256–260. https://doi. org/10.1109/ICCAE.2010.5451705
  • Zhang D, Zhou L. Discovering Golden Nuggets: Data mining in Financial Application, Systems, Man and Cybernetics, Part C: Applications and Reviews. IEEE Transactions. 2004; 34(4):513–522. https://doi.org/10.1109/ TSMCC.2004.829279
  • Rout AK, Dash PK, Rajashree D, Bisoi R. Forecasting Financial Time Series using a Low Complexity Recurrent Neural Network and Evolutionary Learning Approach. Journal of King Saud University-Computer and Information Sciences.2017; 29 (4):536–552. https://doi.org/10.1016/j. jksuci.2015.06.002
  • Dutta S, Shekhar S. Bond rating: A Non-conservative Application of Neural Networks. Proceedings of the IEEE International Conference on Neural Networks. 1998; 2:443–450.
  • Haines LM, et.al. D-optimal Designs for Logistic Regression in Two Variables, mODa 8- Advances in Model-Oriented Designed and Anaysis. Physica-Verlag HD. 2007; 91–98. https://doi.org/10.1007/978-3-7908-1952-6_12
  • Yahoo Finance - Business Finance Stock Market News, [Accessed on August 16, 2018].
  • Selvin S, Vinayakumar R, Gopalakrishnan EA, Menon VK, Soman KP. Stock Price Prediction using LSTM, RNN Mode. International Conference on Advances in Computing, Communications and Informatics (ICACCI). 2017; 1643– 1647. https://doi.org/10.1109/ICACCI.2017.8126078
  • Sirignano J, Cont R. Universal features of Features of Price Formation in Financial Markets: Perspectives from Deep Learning. Quant. Financ. 2019; 19:1449–1459. https://doi. org/10.1080/14697688.2019.1622295
  • Sham VH. Machine Learning Technique for Stock Market Prediction.
  • Khan ZH, Alin TS, Md. Hussain MA. Price Prediction of share market using Artificial Neural Network. International Journal of Computer Application. 2011; 22(2): 42–47. https://doi.org/10.5120/2552-3497
  • Abinaya P, Kumar VS, Balasubramanian P, Menon VK. Measuring Stock Price and Trading Volume Causality among Nifty 50 Stocks: The Toda Yamamoto Method. International Conference on Advances in Computing, Communications and Informatics (ICACCI). 2016:1886– 1890. https://doi.org/10.1109/ICACCI.2016.7732325
  • Li L, Wu Y, Ou Y, Li Q, Zhou Y, Chen D. Research on Machine Learning Algorithms and Feature Extraction for Time Series. IEEE 28th Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC). 2018:1–5. https://doi.org/10.1109/ PIMRC.2017.8292668

Abstract Views: 358

PDF Views: 190




  • Machine Learning and Deep Learning based Approaches to Predict Nifty Index

Abstract Views: 358  |  PDF Views: 190

Authors

P. Karthikeyan
Associate Professor, Department of Management Studies, Kongu Engineering College, Perundurai, Erode, Tamil Nadu, India
N. Vigneshwaran
II MBA, Department of Management Studies, Kongu Engineering College, Perundurai, Erode, Tamil Nadu, India

Abstract


Stock price prediction is one of the most difficult machine learning issues to solve. The stock market, often known as the equity market, has a significant impact on today's economy. This study discusses about different machine learning and deep learning approaches to predict and evaluate stock prices. Time series data is used to depict stock values and algorithms are trained to learn patterns from trends. For the machine learning approaches, study used linear regression, logistic regression and decision tree and for deep learning approaches Long Short-Term Memory (LSTM) and Recurrent Neural Network (RNN) are used to predict Nifty Index value. These variants are commonly used to forecast stock prices and movements. The algorithm is based on the concept of probability and it is used for predictive analysis. For continuous quantitative data, a regression tree is utilized. Linear Regression, Logistic Regression, Decision Tree, LSTM and RNN are the most noticeable techniques used in financial time series forecasting. The study observed from Python software, that the Linear and Logistic Regression model predicts accuracy of roughly 52% and provides an acceptable return ratio. As a result, study found that the Nifty-50 data set has been utilized to improve the precision of supervised learning and future prediction.

Keywords


Decision Tree, Deep Learning, Linear Regression, Logistic Regression and Nifty

References





DOI: https://doi.org/10.15613/hijrh%2F2022%2Fv9i2%2F218195