Fortune Teller: Predicting Your Career Path
Authors: Ye Liu, Luming Zhang, Liqiang Nie, Yan Yan, David Rosenblum
AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on real-world data confirm the accuracy of our model. |
| Researcher Affiliation | Academia | School of Computing, National University of Singapore, Singapore Department of Electric Engineering and Information System, Hefei University of Technology, China Department of Information Engineering and Computer Science, University of Trento, Italy |
| Pseudocode | No | The paper does not contain explicit pseudocode or algorithm blocks. It describes mathematical formulations and optimization steps. |
| Open Source Code | No | The paper does not provide any statement about releasing source code or a link to a code repository. |
| Open Datasets | No | To the best of our knowledge, there is no available benchmark dataset suitable for career path modeling. We thus created new datasets by crawling four popular career paths... We collected the data from About.me1. While About.me is public, the specific dataset created by the authors from About.me is not provided as a downloadable resource, nor is it a standard benchmark dataset with a specific citation providing access to the processed data. |
| Dataset Splits | Yes | The experimental results reported in this paper are based on 10-fold cross-validation. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used to run the experiments, such as GPU/CPU models or memory. |
| Software Dependencies | Yes | In particular, we employed Latent Dirichlet Allocation (LDA) (Blei, Ng, and Jordan 2003) to generate topic distributions... With the assistance of this tool4, we ultimately obtained... (Footnote 4: http://nlp.stanford.edu/software/tmt/tmt-0.4/) |
| Experiment Setup | Yes | To validate our model, we first need to define the time stamps. In particular, we treated the start time of a user s first job as the first time stamp (time t0), and set three years as the time window between two neighboring time stamps... In this work, we examined four successive time stamps for each user... The parameters were selected using grid search. |