Repository files navigation

Can we use the content of news analytics to predict stock price performance? The ubiquity of data today enables investors at any scale to make better investment decisions. The challenge is ingesting and interpreting the data to determine which data is useful, finding the signal in this sea of information. We have used Neural Networks for predicting Apple and Microsoft Stock Prices, feeding our LSTM Network both with the sentiment of Financial News refering the stock and the previous days actual Open price. We suggest the following models to combat the above project:

• LSTM with Stocks Historical Prices and Textblob Sentiment Anaysis
• LSTM with Finbert Sentiment Analysis
• LSTM with Finbert Word Embedding

Finally we compare the above implementation with ARIMA and make some predictions.