Automated predictive analytics with nomogram / Mohammad Nasir Abdullah
In the era of data-driven decision-making, the demand for predictive analytics tools accessible to non-statisticians is rising. Traditional software often requires extensive manual work, hindering efficiency and usability. An innovative application was developed using R programming and the Shiny app...
Saved in:
| Main Author: | |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://ir.uitm.edu.my/id/eprint/105848/1/105848.pdf https://ir.uitm.edu.my/id/eprint/105848/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In the era of data-driven decision-making, the demand for predictive analytics tools accessible to non-statisticians is rising. Traditional software often requires extensive manual work, hindering efficiency and usability. An innovative application was developed using R programming and the Shiny app package to address this gap. This application aims to empower non-statisticians to conduct predictive analytics swiftly and accurately, providing automated processes and delivering relevant results crucial for researchers. The application development involved leveraging R programming and the Shiny app package to create a user-friendly interface for data upload, preprocessing, model building, evaluation, and result interpretation. Advanced statistical techniques such as Fast Backward step-down regression for feature selection, calibration plots, and performance metrics calculation were integrated to ensure robust predictive modelling. The application successfully automates critical aspects of predictive analytics, including data cleaning, feature selection, model building, and validation. Users can upload their datasets, specify variables, choose regression methods, and interpret results through descriptive statistics, visualisations, and model summaries. The app’s automation capabilities significantly reduce manual effort and provide researchers with actionable insights for informed decision-making. In conclusion, the app fills a crucial need by offering non-statisticians a user-friendly platform to conduct predictive analytics efficiently. By automating repetitive tasks and focusing on relevant results, the application empowers researchers to derive meaningful insights from their data, thereby enhancing decision-making processes and driving impactful outcomes across industries. |
|---|