WEKA forecasting
- or -
Post a project like this2069
€149(approx. $160)
- Posted:
- Proposals: 3
- Remote
- #2088757
- OPPORTUNITY
- PRE-FUNDED
- Awarded
Description
Experience Level: Expert
I have the following challenge: I have anonymous historic data on about 150 employees with their historic performance appraisal data (about 20 dimensions of performance appraisal) at two points in time for each employee. I then have data on how well each of them performed on a given task (in 4-5 different performance measures). I want to use AI/machine learning in order to calibrate a forecasting model that allows me to assess employees as of today for which the same kind of historic performance appraisal data (about 20 dimensions of performance appraisal, at two points in time) is available. I want to predict how to best select eg. 10%, or 20% of employees from a group of employees for which the performance appraisal data is available, so that (a) I get the best average expected task performance, (b) minimize the number of selected employees who perform below a given threshold on the new task, (c) minimize task performance variance across the chosen employees, or (d) a combination of these criteria. The model should consider that there is a certain lilkelihood that a given employee selected for the task will resign in the meantime. I want the modelling to be done in WEKA, with robust out of sample testing (e.g. 10 fold cross validation) with a suitable modelling approach of your choice.
Projects Completed
34
Freelancers worked with
31
Projects awarded
59%
Last project
1 Apr 2024
France
New Proposal
Login to your account and send a proposal now to get this project.
Log inClarification Board Ask a Question
-
There are no clarification messages.
We collect cookies to enable the proper functioning and security of our website, and to enhance your experience. By clicking on 'Accept All Cookies', you consent to the use of these cookies. You can change your 'Cookies Settings' at any time. For more information, please read ourCookie Policy
Cookie Settings
Accept All Cookies