SLIDE 1
Large amounts of news data Use deep neural networks to build predictive models Predict market direction of relevant stocks
Applying Deep Learning to Financial Markets with News Data - - PowerPoint PPT Presentation
Applying Deep Learning to Financial Markets with News Data - - PowerPoint PPT Presentation
Applying Deep Learning to Financial Markets with News Data Executive Summary Large amounts of Use deep neural Predict market news data networks to build direction of predictive models relevant stocks Dealing with News Original Workflow
SLIDE 2
SLIDE 3
Dealing with News
Original Workflow
Find interesting articles Make investment decision React in the market Very time consuming Limited scope of articles Missed opportunities Derive implications
SLIDE 4
Dealing with News
Future Workflow
Stream many news articles Link articles with appropriate stocks Determine sentiment scores Determine if market moving React in the market Able to determine sentiment and impact on the market Able to analyze more articles than any human Able to get in and out of market faster
A+
SLIDE 5
Deep Learning
Model Approach - Deep Learning
NVIDIA
abc
Lots of data Feature selection Unstructured data NLP GPU cuDNN Library
SLIDE 6
Current Results
76% F1 Score
News
4 2 1 3 Embedding Input
Model Architecture Model Results Future Considerations
GloVe
A+
LSTM Batch Normalization Softmax 5 Output Link to tickers Sentiment Market Movers Proprietary Embedding Tickers Accuracy Financial Data
$
Positive Neutral Negative
SLIDE 7