The Ranking That Decides the Budget: Deficiency Hotspot Prioritization

The health department must rank 8 districts to allocate a ₹3 crore nutrition intervention fund. Ranking by iron deficiency alone puts District Chittoor at #1. Ranking by a composite of all 3 micronutrients puts District Guntur at #1. Ranking by multi-deficiency prevalence puts District Kurnool at #1. The analyst must determine which ranking method is most defensible — and whether the method is creating the answer rather than revealing it.

# Aplly.xyz Case Study Submission

## Title
The Ranking That Decides the Budget: Deficiency Hotspot Prioritization

## Type
Data Analytics

## Difficulty
Advanced

## Estimated Time
75 minutes

## Overview
The health department must rank 8 districts to allocate a ₹3 crore nutrition intervention fund. Ranking by iron deficiency alone puts District Chittoor at #1. Ranking by a composite of all 3 micronutrients puts District Guntur at #1. Ranking by multi-deficiency prevalence puts District Kurnool at #1. The analyst must determine which ranking method is most defensible — and whether the method is creating the answer rather than revealing it.

## Case Details

Function Focus: Multi-metric ranking sensitivity analysis, composite score design, ranking method bias detection, funding allocation under competing definitions of "worst-off"

Scenario:
The state health department has ₹3 crore for nutrition interventions and needs to rank 8 districts from most-deficient to least-deficient. The minister wants a single ranked list. Three different experts have proposed three different ranking methods: (1) rank by iron deficiency alone (most prevalent single deficiency), (2) rank by a weighted composite score of all 3 nutrients, and (3) rank by multi-deficiency prevalence (percentage of households deficient in 2+ nutrients). Each method produces a different #1 district. The analyst must manually compute all 3 rankings, explain why they disagree, and recommend which method best reflects true need — before the ₹3 crore is allocated.

Dataset Structure:
- 8 districts with deficiency prevalence (%) for 3 micronutrients: iron, vitamin A, zinc
- Also: multi-deficiency prevalence (% of households deficient in 2+ nutrients)
- District population data (for potential per-capita adjustment)

Tasks:
1. Rank the 8 districts by each of the 3 individual nutrient deficiencies separately — produce 3 rankings and identify how many different districts claim the #1 spot
2. Design a weighted composite score (you choose the weights and justify them) — manually compute the composite score for each district and produce a 4th ranking
3. Compute the multi-deficiency ranking (already provided in data — just sort and rank) as a 5th ranking
4. Compare all 5 rankings — identify which district is most sensitive to the ranking method (i.e., its position changes the most) and explain what that district's data profile tells you about why it swings
5. Only after submitting your manual analysis, re-run all 5 rankings in a spreadsheet or AI tool and report any discrepancies — then recommend a single ranking method with a clear justification that the minister can understand

Expected Output:
A ranking analysis memo containing: (a) 3 individual-nutrient rankings, (b) your composite score formula with weight justification and all 8 calculations, (c) the multi-deficiency ranking, (d) a comparison table showing the district with the highest rank volatility and why, (e) a final method recommendation with justification, and (f) a round-trip discrepancy note.

Evaluation Criteria:
Complete and correct rankings under all methods, a well-justified composite score (not arbitrary weights), correct identification of the most rank-sensitive district, a clear explanation of why that district's data causes the swing, and a defensible final recommendation that acknowledges tradeoffs between methods.

## Data Sources

District Deficiency Data:
| District | Population (Lakhs) | Iron Deficiency (%) | Vitamin A Deficiency (%) | Zinc Deficiency (%) | Multi-Deficiency (%) (2+ nutrients) |
|---|---|---|---|---|---|
| Chittoor | 18.2 | 52 | 28 | 35 | 38 |
| Guntur | 22.4 | 48 | 45 | 40 | 52 |
| Kurnool | 15.8 | 38 | 52 | 48 | 55 |
| Anantapur | 16.3 | 45 | 30 | 25 | 30 |
| Kadapa | 12.5 | 35 | 25 | 30 | 28 |
| Prakasam | 14.0 | 42 | 35 | 32 | 36 |
| Nellore | 13.2 | 30 | 20 | 22 | 20 |
| Srikakulam | 11.0 | 55 | 32 | 45 | 48 |

Context:
- Total intervention fund: ₹3 crore
- Allocation rule: top 3 ranked districts split the fund (50%, 30%, 20%)
- Previous year's ranking used iron deficiency alone
- Anantapur's MLA has been lobbying for his district, citing "hidden malnutrition"

Ranking Method Proposals:
| Method | Proposed By | Formula |
|---|---|---|
| Single-nutrient | ICDS Director | Rank by iron deficiency alone |
| Weighted composite | NIN Researcher | Choose weights for Fe, Vit A, Zn (must justify) |
| Multi-deficiency | UNICEF Consultant | Rank by % with 2+ deficiencies |

## Solution Frameworks
Multi-criteria ranking, composite score design, ranking method sensitivity analysis, allocation policy under metric ambiguity

## Solver Guidance & Tutorials
Link to: "When Rankings Contradict — Choosing the Right Metric for Resource Allocation" tutorial

## What You'll Learn
- How different ranking methods produce different "winners" from the same data
- Designing a weighted composite score with explicit, defensible criteria
- Detecting which districts are most sensitive to method choice
- Communicating methodological uncertainty to non-technical decision-makers

## Tags
nutrition ranking, hotspot prioritization, composite scoring, resource allocation, metric sensitivity

## Registration Links
- Register as Solver
- Register as Evaluator

District Deficiency Data:
| District | Population (Lakhs) | Iron Deficiency (%) | Vitamin A Deficiency (%) | Zinc Deficiency (%) | Multi-Deficiency (%) (2+ nutrients) |
|---|---|---|---|---|---|
| Chittoor | 18.2 | 52 | 28 | 35 | 38 |
| Guntur | 22.4 | 48 | 45 | 40 | 52 |
| Kurnool | 15.8 | 38 | 52 | 48 | 55 |
| Anantapur | 16.3 | 45 | 30 | 25 | 30 |
| Kadapa | 12.5 | 35 | 25 | 30 | 28 |
| Prakasam | 14.0 | 42 | 35 | 32 | 36 |
| Nellore | 13.2 | 30 | 20 | 22 | 20 |
| Srikakulam | 11.0 | 55 | 32 | 45 | 48 |

Context:
- Total intervention fund: ₹3 crore
- Allocation rule: top 3 ranked districts split the fund (50%, 30%, 20%)
- Previous year's ranking used iron deficiency alone
- Anantapur's MLA has been lobbying for his district, citing "hidden malnutrition"

Ranking Method Proposals:
| Method | Proposed By | Formula |
|---|---|---|
| Single-nutrient | ICDS Director | Rank by iron deficiency alone |
| Weighted composite | NIN Researcher | Choose weights for Fe, Vit A, Zn (must justify) |
| Multi-deficiency | UNICEF Consultant | Rank by % with 2+ deficiencies |

Multi-criteria ranking, composite score design, ranking method sensitivity analysis, allocation policy under metric ambiguity