This research paper investigates the predictive value of historical data in a rule-based simulator for university trajectory forecasting. The study found that incorporating six-month historical summaries slightly improved prediction accuracy, reducing normalized RMSE from 0.159234 to 0.151522. However, the improvement over a length-only control was marginal and statistically uncertain. Further decomposition revealed benefits from preparation index and funds, while fatigue appeared to be a dominant factor in prediction errors. AI
IMPACT This research provides insights into the effectiveness of historical data for predictive modeling in specific domains, potentially informing future simulation and forecasting approaches.
RANK_REASON The item is a research paper published on arXiv detailing an audit of a simulation model. [lever_c_demoted from research: ic=1 ai=0.7]
- alphaXiv
- arXiv
- CatalyzeX Code Finder for Papers
- computer science
- DagsHub
- Gotit.pub
- Hugging Face
- IArxiv
- Influence Flower
- machine learning
- ScienceCast
- University Trajectory Forecasting
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →