Iteration 0 - OR_EXPERT
Sequence: 1
Timestamp: 2025-07-27 21:52:56

Prompt:
You are an Operations Research (OR) expert focused ONLY on optimization modeling. Your role is to analyze the business domain and design LINEAR optimization problems without involving database design decisions.

CRITICAL MATHEMATICAL CONSTRAINTS FOR LINEAR/MIXED-INTEGER PROGRAMMING:
- The optimization problem MUST be either Linear Programming (LP) or Mixed-Integer Programming (MIP)
- Objective function MUST be linear: minimize/maximize ∑(coefficient × variable)
- All constraints MUST be linear: ∑(coefficient × variable) ≤/≥/= constant
- Decision variables can be continuous (LP) or mixed continuous/integer (MIP)
- NO variable products, divisions, or other nonlinear relationships
- Design business scenarios that naturally lead to linear mathematical formulations
- Generate between 2 and 20 constraints for optimization feasibility

YOUR SCOPE: Focus exclusively on optimization modeling and understanding current schema-to-optimization mapping. Do NOT propose database changes.
ROW COUNT AWARENESS: Be aware that data engineer will apply 3-row minimum rule - tables unable to generate sufficient meaningful rows will be moved to business_configuration_logic.json.

CRITICAL: Respond with ONLY a valid JSON object. No explanations, no markdown, no extra text.

Database: network_2

```sql
CREATE TABLE Person (
  name TEXT,
  age NUMBER,
  city TEXT,
  gender TEXT,
  job TEXT
);
```

```sql
CREATE TABLE PersonFriend (
  name TEXT,
  friend TEXT,
  year NUMBER
);
```



Current Business Configuration Logic: {} (initially empty)

TASK: Design a realistic LINEAR optimization problem and analyze how it maps to the current schema.

JSON STRUCTURE REQUIRED:

{
  "database_id": "network_2",
  "iteration": 0,
  "business_context": "Describe the realistic business scenario that leads to linear optimization (avoid scenarios requiring nonlinear relationships)",
  "optimization_problem_description": "Detailed description of what needs to be optimized using linear objective functions and constraints",
  "optimization_formulation": {
    "objective": "minimize/maximize specific_linear_metric with clear definition (sum of weighted variables only)",
    "decision_variables": "What linear variables can be controlled/decided (continuous or integer)",
    "constraints": "What linear limitations must be respected (no variable products or divisions) - design 2 to 20 constraints"
  },
  
  "current_optimization_to_schema_mapping": {
    "objective_coefficients": {
      "coefficient_name[indices]": {
        "currently_mapped_to": "table.column OR business_configuration_logic.key OR missing",
        "mapping_adequacy": "good/missing/redundant/partial/inaccurate",
        "description": "what this coefficient represents in the optimization model"
      }
    },
    "constraint_bounds": {
      "constraint_name[indices]": {
        "currently_mapped_to": "table.column OR business_configuration_logic.key OR missing", 
        "mapping_adequacy": "good/missing/redundant/partial/inaccurate",
        "description": "what this constraint bound represents"
      }
    },
    "decision_variables": {
      "variable_name[indices]": {
        "currently_mapped_to": "table.column OR business_configuration_logic.key OR missing",
        "mapping_adequacy": "good/missing/redundant/partial/inaccurate", 
        "description": "what this decision variable represents",
        "variable_type": "continuous/integer/binary"
      }
    }
  },
  
  "missing_optimization_requirements": [
    "List what data/parameters are needed for complete linear optimization model"
  ],
  
  "iteration_status": {
    "complete": false,
    "confidence": "low/medium/high",
    "next_focus": "What optimization aspects need refinement"
  }
}

Response:
{
  "database_id": "network_2",
  "iteration": 0,
  "business_context": "A social network company wants to optimize the influence spread within a network by selecting a subset of people to target for a marketing campaign. The goal is to maximize the number of people influenced directly or indirectly through friendships.",
  "optimization_problem_description": "The company needs to decide which individuals to target in order to maximize the total influence spread across the network, considering the friendships between people. Each person targeted has a cost, and there is a budget constraint.",
  "optimization_formulation": {
    "objective": "maximize total_influence = \u2211(influence_coefficient[i] * target[i])",
    "decision_variables": "target[i] is a binary variable indicating whether person i is targeted (1) or not (0)",
    "constraints": [
      "\u2211(cost[i] * target[i]) \u2264 budget",
      "target[i] \u2264 1 for all i",
      "target[i] \u2265 0 for all i"
    ]
  },
  "current_optimization_to_schema_mapping": {
    "objective_coefficients": {
      "influence_coefficient[i]": {
        "currently_mapped_to": "missing",
        "mapping_adequacy": "missing",
        "description": "represents the influence potential of person i in the network"
      }
    },
    "constraint_bounds": {
      "budget": {
        "currently_mapped_to": "missing",
        "mapping_adequacy": "missing",
        "description": "the total budget available for targeting individuals"
      },
      "cost[i]": {
        "currently_mapped_to": "missing",
        "mapping_adequacy": "missing",
        "description": "the cost associated with targeting person i"
      }
    },
    "decision_variables": {
      "target[i]": {
        "currently_mapped_to": "Person.name",
        "mapping_adequacy": "partial",
        "description": "binary decision variable indicating if person i is targeted",
        "variable_type": "binary"
      }
    }
  },
  "missing_optimization_requirements": [
    "Influence coefficients for each person",
    "Cost associated with targeting each person",
    "Total budget for the campaign"
  ],
  "iteration_status": {
    "complete": false,
    "confidence": "medium",
    "next_focus": "Determine influence coefficients and costs for each person, and define the total budget"
  }
}
