ABSTRACT
There has been a lot of attempts in building predictive models that
can correctly predict the stock price. However, most of these models
only focus on different in-market factors such as the prices of other
similar stocks. This paper discusses the efficiency/accuracy
of three different neural network models (feedforward, recurrent,
and convolutional) in predicting stock prices based on external
dependencies such as oil price, weather indexes, etc.

Software architecture

Links:

• Github Link
• Research Paper