Neural net for predicting work inclination based on a person's CV

I have a large database of CVs, of both employed and unemployed individuals. All of the CVs are exported in an html format and follow a uniform format with standard fields and sections (name, address, education, work experience, hobbies, etc) The purpose of this project is to program and train a neural net for estimating the likelihood of each person being inclined to leave his current job and join a startup company for the first time in his life within the next year (ie someone who is currently or at any time in the past worked in a startup would be considered to have zero likelihood). The net should take into account as many parameters as possible from the CVs in order to be more accurate and to potentially find various hidden connections. The output should be a number between 0 and 1 for each CV, plus optionally add some parameter to indicate the expected value of how much time from now that person is most likely to actually start that new startup job. I'll provide you with some additional data that should make this job easier: 1. a small % of the people in the database were asked directly which resulted in "yes", "no", or "no answer" for each one. 2. A table classifying every company in the database ( ie past or present employers ) as either a startup or a non-startup. 3. Approximate numbers (fairly accurate) of the total number of people starting to work in a startup, for the first time, from each geographical region. **SEE MORE DETAILS IN THE "DELIVERABLES" SECTION Please write in your bid comment: What relevant experience do you have? What special challenges/difficulties do you foresee with this project? Would you like to include the optional part I mentioned above? If so, how do you roughly plan to approach it? Which language would you prefer to use for this and with which libraries? Can you program this in Python? Thank you for your answers and for placing your bid. ## Deliverables By looking at the chronology of each CV you should be able to generate a huge amount of training data for the net, automatically. E.g. if you see a person who started for the first time in his life to work in a startup in Jan 2007, you can use the state of his CV from Jan 2006 to dec 2006 as a sample of a CV that, at those points in time, should have been given a high likelihood. other CV states (ie when a first startup job wasn't started within a year) can be used for training the net as a low likelihood. Just to clarify, "the state of the cv in a past point in time" means whatever is left in the cv after discarding all information on events that took place after that point in time, eg a change of jobs. Information that may not have necessarily changed, eg hobbies, should remain intact when taking a cv "back in time" for the sake of training. You should make use of data set 3 by, eg, "binning". Your job will also include writing the simple code that extracts from the HTML the relevant bits of information. You may use any popular parser or relevant library for that, eg beautifulsoup or xpath. ======================= 1) All deliverables will be considered "work made for hire" under U.S. Copyright law. Employer will receive exclusive and complete copyrights to all work purchased. (No GPL, GNU, 3rd party components, etc. unless all copyright ramifications are explained AND AGREED TO by the employer on the site per the worker's Worker Legal Agreement). 2) Complete and fully-functional working program(s) in executable form as well as complete source code of all work done. 3) Deliverables must be in ready-to-run condition, as follows (depending on the nature of the deliverables): a) For web sites or other server-side deliverables intended to only ever exist in one place in the Employer's environment--Deliverables must be installed by the Worker in ready-to-run condition in the Employer's environment. b) For all others including desktop software or software the employer intends to distribute: A software installation package that will install the software in ready-to-run condition on the platform(s) specified in this project. ## Platform Neural network, Python (preferable) or other language