First off, you are permitted to use open source learning implementations, and are *strongly* encouraged to do so to save yourself much hassle. The majority of this project should be to research implementations, and just test that you can get it up and running and that it runs suitable with the data formats I have. The data involves a SQL databases containing a table of weather information: date, city, high, low, avgerage temperature along with a second table consisting of news story (headlines) pertaining to the weather: date, city, news headline. Pretty simple dataset. Your job will be to take a learning algorithm and appy it to the data. I do not require you to run to a full solution, however you must be certain it will work without much work. Neural network libs to look at include 'NeuralJ' 'Neural Network Utility' and 'Neural Network Utility' The neural network should look for both trends in the data, as well tie in with the news headlines for keywords that elicit change. It should also look at the # of new stories per day/range, etc. It should be extensible later if I wish to add additional columns like humidity, etc, but I thought I would keep it simple to begin with. The database in question is postgres. It should be written in Java, but I am open to other solutions, including C++
## Deliverables
1) Complete and fully-functional working program(s) in executable form as well as complete source code of all work done.
2) Deliverables must be in ready-to-run condition, as follows (depending on the nature of the deliverables):
A software installation package that will install the software in ready-to-run condition on the platform(s) specified in this bid request.
3) All deliverables will be considered "work made for hire" under U.S. Copyright law. Buyer will receive exclusive and complete copyrights to all work purchased.
## Platform
Windows is required, but with a java app, it should run on any platform.