lwbakhit / lstm_stock_predictor

LSTM Stock Predictor

Due to the volatility of cryptocurrency speculation, investors will often try to incorporate sentiment from social media and news articles to help guide their trading strategies. One such indicator is the Crypto Fear and Greed Index (FNG) which attempts to use a variety of data sources to produce a daily FNG value for cryptocurrency. You have been asked to help build and evaluate deep learning models using both the FNG values and simple closing prices to determine if the FNG indicator provides a better signal for cryptocurrencies than the normal closing price data.

In this assignment, you will use deep learning recurrent neural networks to model bitcoin closing prices. One model will use the FNG indicators to predict the closing price while the second model will use a window of closing prices to predict the nth closing price.

Use the above to answer the following:

Which model has a lower loss?

 The "closing model" has a lower loss. 

Which model tracks the actual values better over time?

 The "closing model" tracks the actual values more accurately over time. 

Which window size works best for the model?

 A window size of 10 provides the most accurate results, as it takes a longer time period into consideration for the predictions. 

---

Resources

Keras Sequential Model Guide

Illustrated Guide to LSTMs

Stanford's RNN Cheatsheet