Summary of Impact Of Comprehensive Data Preprocessing on Predictive Modelling Of Covid-19 Mortality, by Sangita Das et al.
Impact of Comprehensive Data Preprocessing on Predictive Modelling of COVID-19 Mortality
by Sangita Das, Subhrajyoti Maji
First submitted to arxiv on: 15 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper evaluates the impact of a custom data preprocessing pipeline on machine learning models predicting COVID-19 mortality trends using Our World in Data (OWID) data. The pipeline differs from standard processing through four key steps: transforming weekly reports into daily updates to correct biases, localised outlier detection and processing to preserve variance, utilising computational dependencies for consistency, and iterative feature selection to optimise the feature set. Results show significant improvement with the custom pipeline, with the MLP Regressor achieving a test RMSE of 66.556 and R-squared of 0.991, surpassing the DecisionTree Regressor from the standard pipeline. The findings highlight the importance of tailored preprocessing techniques in enhancing predictive modelling accuracy for COVID-19 mortality. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study shows how to make better predictions about COVID-19 deaths using special methods to prepare data. They compared different ways of preparing data and found that a custom approach worked much better than usual. By correcting mistakes, removing weird outliers, and making sure the numbers add up, they were able to get more accurate results. This is important because it helps us understand and predict COVID-19 trends, which can inform decisions about how to deal with the pandemic. |
Keywords
» Artificial intelligence » Feature selection » Machine learning » Outlier detection
