ABSTRACT:
The recent advance of deep learning has enabled trading algorithms to predict stock price movements more accurately. Unfortunately, there is a significant gap in the real-world deployment of this breakthrough. For example, professional traders in their long-term careers have accumulated numerous trading rules, the myth of which they can understand quite well. On the other hand, deep learning models have been hardly interpretable. This paper presents Deep Clue, a system built to bridge text-based deep learning models and end users through visually interpreting the key factors learned in the stock price prediction model. We make three contributions in Deep Clue. First, by designing the deep neural network architecture for interpretation and applying an algorithm to extract relevant predictive factors, we provide a useful case on what can be interpreted out of the prediction model for end users. Second, by exploring hierarchies over the extracted factors and displaying these factors in an interactive, hierarchical visualization interface, we shed light on how to effectively communicate the interpreted model to end users. Specially, the interpretation separates the predictable from the un-predictable for stock prediction through the use of intercept model parameters and a risk visualization design. Third, we evaluate the integrated visualization system through two case studies in predicting the stock price with financial news and company-related tweets from social media. Quantitative experiments comparing the proposed neural network architecture with state-of-the-art models and the human baseline are conducted and reported. Feedbacks from an informal user study with domain experts are summarized and discussed in details. The study results demonstrate the effectiveness of Deep Clue in helping to complete stock market investment and analysis tasks
EXISTING SYSTEM
The new development of profound learning has empowered exchanging calculations to anticipate stock value developments all the more precisely. Sadly, there is a huge hole in reality sending of this leap forward. For instance, proficient dealers in their drawn out vocations have amassed various exchanging rules, the legend of which they can see very well. Then again, profound learning models have been not really interpretable. This paper presents Deep Clue, a framework worked to connect text-based profound learning models and end clients through outwardly deciphering the key elements learned in the stock value forecast model. We make three commitments in Deep Clue. To begin with, by planning the profound neural organization engineering for translation and applying a calculation to extricate important prescient variables.
PROPOSED SYSTEM
We give a helpful case on what can be deciphered out of the expectation model for end clients. Second, by investigating pecking orders over the extricated factors and showing these components in an intelligent, progressive representation interface, we shed light on step by step instructions to viably impart the deciphered model to end clients. Uncommonly, the understanding isolates the predictable from the un-predictable for stock expectation using capture model boundaries and a danger perception plan. Third, we assess the coordinated representation framework through two contextual analyses in anticipating the stock cost with online monetary news and friends related tweets from web-based media. Quantitative analyses contrasting the proposed neural organization engineering and cutting edge models and the human gauge are directed and revealed.
SYSTEM REQUIREMENTS
SOFTWARE REQUIREMENTS:
• Programming Language : Python
• Font End Technologies : TKInter/Web(HTML,CSS,JS)
• IDE : Jupyter/Spyder/VS Code
• Operating System : Windows 08/10
HARDWARE REQUIREMENTS:
Processor : Core I3
RAM Capacity : 2 GB
Hard Disk : 250 GB
Monitor : 15″ Color
Mouse : 2 or 3 Button Mouse
Key Board : Windows 08/10
