Analysis and Prediction of Stock Market Trends Using Deep Learning Harshit Agarwal, Gaurav Jariwala and Akshit Shah Abstract The paper proposes a progressive conclusion on the application of recurrent neural networks in stock price forecasting. We have also used random forest classifier to factor in the sudden fluctuations in stock prices which are derivatives of any abnormal events. Machine learning and deep learning strategies are being used by many quantitative hedge funds to increase their returns. Finance data belongs to time series data. A time series is a series of data points indexed in time. The nonlinearity and chaotic nature of the data can be combated using recurrent neural networks which are effective in tracing relationships between historical data and using it to predict new data. Historical data in this context is time series data from the past. It is one of the most important and the most valuable parts for speculating about future prices. Long short-term memory (LSTM) is capable of capturing the most important features from time series data and modelling its dependencies. Building a good and effective prediction system can help investors and traders to get a glimpse of the future direction of the stock and accordingly help them mitigate risk in their respective portfolios. The results obtained by our approach are accurate up to 97% for the values predicted using historic data and 67% for the trend prediction using news headlines. Keywords Activation function · Back-propagation · Long-term short memory · Random forest classifier · Recurrent neural network · Sentimental analysis H. Agarwal (B ) · G. Jariwala · A. Shah Sarvajanik College of Engineering and Technology, Surat, India e-mail: 9arshit@gmail.com G. Jariwala e-mail: gjariwala9@gmail.com A. Shah e-mail: shahakshit34@gmail.com © Springer Nature Singapore Pte Ltd. 2020 P. K. Singh et al. (eds.), Proceedings of First International Conference on Computing, Communications, and Cyber-Security (IC4S 2019), Lecture Notes in Networks and Systems 121, https://doi.org/10.1007/978-981-15-3369-3_39 521