This repository contains my complete submission for the MoSPI GOIStats Hackathon 2025 organized by the Ministry of Statistics and Programme Implementation (MoSPI), Government of India. The work was conducted between March 27 and April 1, 2025.
It includes all required documents, analysis, and R code used for the competition, with an aim to encourage transparency, reproducibility, and further refinement of the insights and methodologies I developed.
During the hackathon, participants were required to submit four distinct files. You can access mine below:
-
📄 R Code File (PDF Format)
Contains all the R code I used during the hackathon.
🔗 All R Codes (PDF) -
📄 Data Sources Documentation
Describes the datasets I used, including where they were sourced from and how they can be accessed.
🔗 Data Sources -
📄 Methodology Document
Explains my step-by-step approach, objectives behind each plot and model, and detailed reasoning and interpretations.
🔗 Methodology -
📄 Analytical Insights and Policy Recommendations
Provides in-depth analysis, key findings, and actionable suggestions for potential improvements in policy formulation.
🔗 Final Analysis & Recommendations
To ensure reproducibility and foster further analysis or extension of this work, I've made both the source code and dataset publicly available.
-
📌 R Code File
CPI_F&B.R -
📌 Dataset
CPIndex_Jan13-To-Jan25_F&B.csv
Feel free to clone the repository, explore the code, rerun the analysis, or extend it with additional insights. Contributions and feedback are always welcome!
The aim of making this repository public is to:
- Enable reproducibility of the submitted results.
- Encourage other data scientists, economists, and statisticians to review and improve the work.
- Promote collaboration on real-world policy data analysis.
- Invite feedback that can help in identifying unexplored directions and better conclusions.
This submission reflects my work during the limited time frame of the hackathon. I acknowledge that some parts can be optimized or improved further. As time permits, I plan to revisit this project and incorporate more fine-grained updates and refinements.
If you're exploring this repository after finding my LinkedIn post — welcome!
Whether you're a policymaker, fellow participant, data scientist, or enthusiast, I’d love to hear your thoughts or ideas for enhancement.
Feel free to connect with me on LinkedIn or raise an issue/discussion in this repo.