Predicting the movement of any commodity market is a complex endeavor. Recent studies have shown promising results in applying sentiment analysis methods to stock markets and the Seeker would like to explore the use of similar analysis techniques to aid in the prediction of the world steel market. The Seeker desires an algorithm that takes as input various qualitative data sources such as RSS feeds with news and blogs related to the steel industry and produces a greed/fear numerical index to be used as an input to a complete forecasting model.
Sentiment analysis is being used in a wide variety of fields to provide analysis of such things as customer feedback, effectiveness of advertising campaigns, and political polling responses. Typically, sentiment analysis utilizes Natural Language Processing (NLP) and other artificial intelligence techniques to analyze textual data and derive quantitative data from subjective information. Recently published work has shown its applicability to forecasting stock market trends and the Seeker believes it can be used to improve its steel market forecasting methodology. The Seeker is looking for an algorithm that takes as input various data sources such as RSS feeds with news and blogs related to the steel industry and produces a greed/fear numerical index to be used as an input to a complete forecasting model. Solutions may utilize a suggested RSS feed but Solvers are also encouraged to find additional qualitative sources to enhance their algorithm.
The submission to the Challenge should include the following:
- A detailed description of the proposed Solution addressing specific Technical Requirements presented in the Detailed Description of the Challenge. This should also include a thorough description of the algorithm used in the Solution accompanied by a well-articulated rationale for the method employed.
- Output from the proposed algorithm. Output must be in the form described in the Detailed Description of the Challenge.
- For top ranked submissions, the Seeker may request source code and/or an executable with sufficient documentation to enable the Seeker to compile, execute the algorithm, and validate the method using additional validation data sets.
The Challenge award is contingent upon theoretical evaluation of the method/algorithm by the Seeker, and validation by the Seeker of the submitted reduction to practice Solution.
To receive an award, the Solvers will not have to transfer their exclusive IP rights to the Seeker. Instead, Solvers will grant to the Seeker a non-exclusive license to practice their solutions.
Awards:- $20,000
Deadline:- 03-05-2021
