A Novel Approach for Stock Price Prediction
DOI:
https://doi.org/10.18486/ijcsnt/8.3.109Keywords:
Stock Price Prediction, LSTM, FB Prophet, Time Series Data, PythonAbstract
Stock market has always attracted people from all backgrounds. With great returns stock market investment comes with great risks. In this paper, we propose a time-series prediction model using Long Short Term Memory - LSTM to forecast the stock market trend based on the technical analysis using historical data. We also propose the FB PROPHET model which is more robust in time series forecasting. This model automates the process of forecasting stock market trends helping individuals to buy, sell, or hold their stocks. The obtained results showed the time series prediction model has great potential for short-term predictions.
References
Ravindra Babu Ravula. Prophet: Forecasting at Scale. https://research.fb.com/prophet-forecasting-at-scale/. Online.
Towards Data Science. Predicting Stock Price with LSTM. https://towardsdatascience.com/predicting-stock-price-with-lstm-13af86a74944. Online.
Olah C. Understanding LSTMs. https://colah.github.io/posts/2015-08-Understanding-LSTMs/, 2015. Online.
Banerjee D. Forecasting of Indian stock market using time series Prophet model. In 2nd IEEE International Conference on Business and Information Management (ICBIM), pp. 131–135. DOI: https://doi.org/10.1109/ICBIM.2014.6970973
Xing T, Sun Y, Wang Q et al. The analysis and prediction of stock prices. In IEEE International Conference on Granular Computing (GrC), pp. 368–373. DOI: https://doi.org/10.1109/GrC.2013.6740438
Patnaik LM. Forecasting stock time-series using data approximation and pattern sequence similarity. International Journal of Information Processing (IJIP) 2013; 90–100.
Chouhan L, Agarwal N, Parmar I et al. Stock market prediction using machine learning. DOI: 10.1109/ICSCCC.2018.870333.
Downloads
Published
Issue
Section
License
Copyright (c) 2019 Vivek Singh Kushwah, Taran Gangil, Manish Dixit
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
