Challenge 1
The team produced a data‑driven risk heuristics analysis pipeline that combines Python analytics with large language model feedback to assess and enrich existing risk registers. Using Jupyter notebooks, they analyse risk and mitigation data, apply SME heuristics via an LLM, and output annotated spreadsheets and summary datasets designed for downstream Power BI dashboards.
Please be aware that this content was generated follwing an automated review so may not be perfectly accurate; refer to the original challenge brief and team files for authoritative information
Improved visibility of weak or incomplete risks and mitigations; faster identification of data gaps and risk hotspots; more consistent application of SME heuristics at scale; better decision support through structured analytics outputs.
analysis1.ipynb: Main notebook analysing risk data, applying SME heuristics via an LLM, and generating annotated outputs.Data Analysis & Cleaning - Python/Data Analysis_1.ipynb: Supporting notebook for cleaning, merging, and preparing risk and mitigation datasets.Front End/merged_risk_mit.csv: Combined risk and mitigation dataset used for analysis and reporting.
team: Risk Hacktory members: tbc topics: solution-centre, hack26, challenge1, python, pandas, jupyter, google-gemini, openpyxl, power-bi, risk-management, heuristics, data-analysis, large-language-models, data-quality, project-risk, analytics, automation technologies: python, pandas, jupyter, google-gemini, openpyxl, power-bi