The stock market is volatile and is subject to fluctuations. There are many factors like news, fundamental indicators, and heuristic technical indicators et cetera which contribute to such fluctuations. The randomness and volatility have drawn the attention of many researchers and perplexed them. Algorithm trading has been gaining popularity, as machines are able to process tons of data. The ability of an algorithm to predict the price movement gives an opportunity to gain a fortune from the stock market. In this paper, we study the historical prices, calculate the technical indicators based on them, apply feature selection to remove multicollinearity and find the most important features affecting the prices before processing it into the LSTM network to predict the price movement. The prediction of market value can help maximize the profit while keeping the risk comparatively low.

Stock prediction, Technical Indicators, Feature Selection, XGBoost, LSTM, Neural Network

[1] P. Aithal, A. Dinesh and M. Geetha, "Identifying Significant Macroeconomic Indicators for Indian Stock Markets", IEEE Access, vol. 7, pp. 143829-143840, 2019.
[2] M. Firdaus, S. Pratiwi, D. Kowanda and A. Kowanda, "Literature review on Artificial Neural Networks Techniques Application for Stock Market Prediction and as Decision Support Tools", Third International Conference on Informatics and Computing (ICIC), 2018
[3] Y. Snezhko, "The use of technical analysis indicators in the Russian stock market", Russian Journal of Entrepreneurship, vol. 16, no. 16, p. 2681, 2015.
[4] Blume, L.,Easley, D., O`Hara, M, “Market Statistics and Technical Analysis: The Role of Volume. The Journal of Finance”, Wiley online Library, 1994.
[5] Iain M. Johnstone1 and D. Michael Titterington, Padhy S, “Statistical challenges of high-dimensional data”, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 367, Issue.1906, pp. 175-195, 2009.
[6] Mela, C. and K. Kopalle, “The impact of collinearity on regression analysis: the asymmetric eVect of negative and positive correlations”, Applied Economics, Vol. 34, pp. 667-677, 2002.
[7] Yuqinq He, Kamaladdin Fataliyev, and Lipo Wang, “Feature Selection for Stock Market Analysis”, International Conference on Neural Information Processing, Vol. 8227, pp. 737-744, 2013.
[8] M. H., E.A., G., Menon, V. and K.P., S., “NSE Stock Market Prediction Using Deep-Learning Models”, Procedia Computer Science, Vol. 132, Issue.4, pp. 1351-1362, 2018.
[9] A. Kumar, J. S. Saini, “Stock Data Analysis and Prediction in Machine Learning”, IJCSE, Vol.8, Issue.9, pp.70-78, 2020.
[10] P. Kanade, "Machine Learning Model for Stock Market Prediction", International Journal for Research in Applied Science and Engineering Technology, vol. 8, no. 6, pp. 209-216, 2020.
[11] J. Patel, S. Shah, P. Thakkar and K. Kotecha, "Predicting stock and stock price index movement using Trend Deterministic Data Preparation and machine learning techniques", Expert Systems with Applications, vol. 42, no. 1, pp. 259-268, 2015.
[12] Acheme, David & Vincent, Olufunke & Folorunso, Olusegun & Isaac, Olusola, “A Predictive Stock Market Technical Analysis Using Fuzzy Logic”, International Conference on Neural Information Processing, Vol. 7, Issue.3,2014.
[13] Lee H, Surdeanu M, MacCartney B, Jurafsky D, “On the Importance of Text Analysis for Stock Price Prediction”, Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC`14), pp. 1170–1175, 2014
[14] A.Sahoo, J.K.Mantri, “Stock Market Prediction Using Text Mining Approaches: A Survey”, IJCSE, Vol. 7, Issue.2, pp. 443-450, 2019.
[15] V. Ingle, S. Deshmukh, “Predictive mining for stock market based on live news TF-IDF features”, International Journal of Autonomic Computing, Vol.2 No.4, pp. 341-345,2017.