Predicting Stock Market Trends using Hybrid SVM Model and LSTM with Sentiment Determination using Natural Language Processing

Abstract

In the financial world, stock trading is one of the most crucial activities. Investors make educated guesses to predict stock market trends by analyzing news, studying the company history, industrial history and a lot of other data. successfully predicting the stock market trends and investing in the right shares at the right time can maximize the investor’s profit or at least minimize the losses. Stock market price data is generated in huge volumes and is affected by various diverse factors. This work proposes two models to predict the stock market prices. The first model is an LSTM model that employs a backpropagation optimized LSTM network to forecast future stock prices. The second model is a hybrid model that combines an SVM model, KNN model and a Random Forest classifier using the Majority Voting algorithm to predict stock market trends. Both models have a sentiment analyzer to factor the news influencing the stock market using Natural Language Processing (NLP). The project aims to help investors who are new to the stock market and don’t possess sufficient knowledge to make share investments as well the experienced investors by predicting stock market trends.

Predicting Financial Time Series for Value Investment

“…Simple models as regression, multi-layer perceptron and Hidden Markov Models can beat the market and provide a gain greater than one [6]. A type of network that is widely explored is the Long Short Term Memory [7,8].…”

Stock Price Forecasting for Jordan Insurance Companies Amid the COVID-19 Pandemic Utilizing Off-the-Shelf Technical Analysis Methods

“…Stock market forecasting refers to the actions made to provide interested parties, such as investors and customers, with a predictable picture of the future direction and variation of the object price. Investors could make successful decisions or prevent losses if they could accurately forecast future stock prices (Singh et al 2019(Singh et al , 2021Sunny et al 2020;Lin et al 2020;Shynkevich et al 2017;Mehta et al 2021;Zhuo et al 2021).…”