Iteration 2 - OR_EXPERT_REFINEMENT
Sequence: 5
Timestamp: 2025-07-25 22:51:52

Prompt:
You are an Operations Research (OR) expert in iteration 2 of an alternating optimization process. The algorithm alternates between OR expert analysis and data engineering implementation until convergence.

CRITICAL MATHEMATICAL CONSTRAINTS FOR LINEAR/MIXED-INTEGER PROGRAMMING:
- The optimization problem MUST remain 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
- If previous iteration introduced nonlinear elements, redesign as linear formulation
- Maintain between 2 and 20 constraints for optimization feasibility

YOUR SCOPE: Focus exclusively on optimization modeling and mapping analysis. Do NOT propose database changes.
ROW COUNT AWARENESS: Understand that data engineer applies 3-row minimum rule - insufficient table data gets moved to business_configuration_logic.json.


DATA AVAILABILITY CHECK: 
Before listing missing requirements, verify:
- Check current schema for required data columns
- Check business configuration logic for required parameters  
- Only list as "missing" if data is truly unavailable
- If all mappings are "good", missing_requirements should be []

CONSISTENCY RULES:
- IF all mapping_adequacy == "good" THEN missing_optimization_requirements = []
- IF missing_optimization_requirements = [] THEN complete CAN be true
- IF complete == true THEN confidence should be "high"

SELF-CHECK: Before responding, verify:
1. Does current schema contain the data I claim is missing?
2. Are my mapping assessments consistent with missing requirements?
3. Is my complete status consistent with missing requirements?

MAPPING COMPLETENESS CHECK: Ensure logical consistency between:
- All objective coefficients mapped with adequacy evaluation
- All constraint bounds mapped with adequacy evaluation  
- All decision variables mapped with adequacy evaluation
- Missing requirements list matches inadequate mappings only


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



CURRENT STATE (iteration 1):
{
  "iteration": 2,
  "converged": false,
  "business_context": "A media company aims to maximize the total viewership share across its channels by optimally scheduling programs. The company needs to decide which programs to broadcast on which channels and at what times of day, considering channel ratings and program origins, while ensuring linearity in the optimization model.",
  "optimization_problem": "The goal is to maximize the total viewership share by selecting the best combination of programs, channels, and times of day. The objective is to maximize the sum of the products of program shares and channel ratings. Constraints include ensuring each program is broadcast at most once, each channel has a limited number of time slots, and programs from certain origins are prioritized.",
  "objective": "maximize \u2211(Share_in_percent[Channel_ID, Program_ID] \u00d7 Rating_in_percent[Channel_ID] \u00d7 x[Channel_ID, Program_ID, Time_Slot_ID])",
  "table_count": 2,
  "key_changes": [
    "Schema changes include creating tables for program shares and channel ratings to address missing optimization requirements. Configuration logic updates include scalar parameters for channel ratings and program shares."
  ],
  "math_consistency": "high",
  "next_iteration_focus": "Obtain data for Share_in_percent[Channel_ID, Program_ID] and Rating_in_percent[Channel_ID] to complete the linear formulation",
  "mapping_adequacy_summary": "partially_adequate"
}

CURRENT SCHEMA:
```sql
-- Iteration 2 Database Schema
-- Objective: Schema changes include creating tables for program shares and channel ratings to address missing optimization requirements. Configuration logic updates include scalar parameters for channel ratings and program shares.

CREATE TABLE time_slots (
  time_slot_id INTEGER,
  time_of_day STRING
);

CREATE TABLE program_origins (
  program_id INTEGER,
  origin STRING
);

CREATE TABLE broadcast_decisions (
  channel_id INTEGER,
  program_id INTEGER,
  time_slot_id INTEGER,
  x BOOLEAN
);

CREATE TABLE program_shares (
  channel_id INTEGER,
  program_id INTEGER,
  share_in_percent INTEGER
);

CREATE TABLE channel_ratings (
  channel_id INTEGER,
  rating_in_percent INTEGER
);


```

CURRENT DATA DICTIONARY:
{
  "tables": {
    "time_slots": {
      "business_purpose": "Available time slots for broadcasting programs",
      "optimization_role": "business_data",
      "columns": {
        "time_slot_id": {
          "data_type": "INTEGER",
          "business_meaning": "Unique identifier for a time slot",
          "optimization_purpose": "Used in decision variables",
          "sample_values": "1, 2, 3"
        },
        "time_of_day": {
          "data_type": "STRING",
          "business_meaning": "Time of day for broadcasting",
          "optimization_purpose": "Used in decision variables",
          "sample_values": "Morning, Afternoon, Evening"
        }
      }
    },
    "program_origins": {
      "business_purpose": "Origin of programs (e.g., local, international)",
      "optimization_role": "business_data",
      "columns": {
        "program_id": {
          "data_type": "INTEGER",
          "business_meaning": "Unique identifier for a program",
          "optimization_purpose": "Used in decision variables",
          "sample_values": "1, 2, 3"
        },
        "origin": {
          "data_type": "STRING",
          "business_meaning": "Origin of the program",
          "optimization_purpose": "Used in constraints",
          "sample_values": "Local, International"
        }
      }
    },
    "broadcast_decisions": {
      "business_purpose": "Binary decisions indicating if a program is broadcast on a channel at a specific time",
      "optimization_role": "decision_variables",
      "columns": {
        "channel_id": {
          "data_type": "INTEGER",
          "business_meaning": "Unique identifier for a channel",
          "optimization_purpose": "Used in decision variables",
          "sample_values": "1, 2, 3"
        },
        "program_id": {
          "data_type": "INTEGER",
          "business_meaning": "Unique identifier for a program",
          "optimization_purpose": "Used in decision variables",
          "sample_values": "1, 2, 3"
        },
        "time_slot_id": {
          "data_type": "INTEGER",
          "business_meaning": "Unique identifier for a time slot",
          "optimization_purpose": "Used in decision variables",
          "sample_values": "1, 2, 3"
        },
        "x": {
          "data_type": "BOOLEAN",
          "business_meaning": "Binary decision variable",
          "optimization_purpose": "Used in decision variables",
          "sample_values": "0, 1"
        }
      }
    },
    "program_shares": {
      "business_purpose": "Share of viewership for a program on a channel",
      "optimization_role": "objective_coefficients",
      "columns": {
        "channel_id": {
          "data_type": "INTEGER",
          "business_meaning": "Unique identifier for a channel",
          "optimization_purpose": "Used in objective coefficients",
          "sample_values": "1, 2, 3"
        },
        "program_id": {
          "data_type": "INTEGER",
          "business_meaning": "Unique identifier for a program",
          "optimization_purpose": "Used in objective coefficients",
          "sample_values": "1, 2, 3"
        },
        "share_in_percent": {
          "data_type": "INTEGER",
          "business_meaning": "Share of viewership for a program on a channel",
          "optimization_purpose": "Used in objective coefficients",
          "sample_values": "50, 60, 70"
        }
      }
    },
    "channel_ratings": {
      "business_purpose": "Rating of a channel",
      "optimization_role": "objective_coefficients",
      "columns": {
        "channel_id": {
          "data_type": "INTEGER",
          "business_meaning": "Unique identifier for a channel",
          "optimization_purpose": "Used in objective coefficients",
          "sample_values": "1, 2, 3"
        },
        "rating_in_percent": {
          "data_type": "INTEGER",
          "business_meaning": "Rating of a channel",
          "optimization_purpose": "Used in objective coefficients",
          "sample_values": "75, 80, 85"
        }
      }
    }
  }
}


CURRENT BUSINESS CONFIGURATION LOGIC:
{
  "Share_in_percent": {
    "sample_value": 50,
    "data_type": "INTEGER",
    "business_meaning": "Share of viewership for a program on a channel",
    "optimization_role": "Objective coefficient",
    "configuration_type": "scalar_parameter"
  },
  "Rating_in_percent": {
    "sample_value": 75,
    "data_type": "INTEGER",
    "business_meaning": "Rating of a channel",
    "optimization_role": "Objective coefficient",
    "configuration_type": "scalar_parameter"
  }
}


TASK: Refine the optimization problem formulation by analyzing current data schema mapping and identifying requirements while maintaining LINEAR structure.

JSON STRUCTURE REQUIRED:

{
  "database_id": "program_share",
  "iteration": 2,
  "business_context": "Updated realistic business scenario description that supports linear optimization",
  "optimization_problem_description": "Refined description of LINEAR optimization problem", 
  "optimization_formulation": {
    "objective": "refined linear minimize/maximize with mathematical precision (sum of weighted variables only)",
    "decision_variables": "clearly defined controllable linear variables (continuous or integer)",
    "constraints": "mathematically precise LINEAR constraint definitions (no variable products or divisions) - maintain 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 still needed for linear formulation (should be [] if all mappings are good)"
  ],
  
  "iteration_status": {
    "complete": true/false based on linear formulation completeness,
    "confidence": "updated confidence level",
    "next_focus": "What needs refinement for linear optimization OR 'Ready for convergence'"
  }
}

Response:
{
  "database_id": "program_share",
  "iteration": 2,
  "business_context": "A media company aims to maximize the total viewership share across its channels by optimally scheduling programs. The company needs to decide which programs to broadcast on which channels and at what times of day, considering channel ratings and program shares, while ensuring linearity in the optimization model.",
  "optimization_problem_description": "The goal is to maximize the total viewership share by selecting the best combination of programs, channels, and times of day. The objective is to maximize the sum of the products of program shares and channel ratings, ensuring each program is broadcast at most once, each channel has a limited number of time slots, and programs from certain origins are prioritized.",
  "optimization_formulation": {
    "objective": "maximize \u2211(Share_in_percent[Channel_ID, Program_ID] \u00d7 Rating_in_percent[Channel_ID] \u00d7 x[Channel_ID, Program_ID, Time_Slot_ID])",
    "decision_variables": "x[Channel_ID, Program_ID, Time_Slot_ID] (binary)",
    "constraints": [
      "\u2211(x[Channel_ID, Program_ID, Time_Slot_ID]) \u2264 1 for all Program_ID (each program is broadcast at most once)",
      "\u2211(x[Channel_ID, Program_ID, Time_Slot_ID]) \u2264 Max_Time_Slots[Channel_ID] for all Channel_ID (each channel has a limited number of time slots)",
      "\u2211(x[Channel_ID, Program_ID, Time_Slot_ID]) \u2265 Min_Local_Programs for all Channel_ID (minimum number of local programs per channel)"
    ]
  },
  "current_optimization_to_schema_mapping": {
    "objective_coefficients": {
      "Share_in_percent[Channel_ID, Program_ID]": {
        "currently_mapped_to": "program_shares.share_in_percent",
        "mapping_adequacy": "good",
        "description": "Share of viewership for a program on a channel"
      },
      "Rating_in_percent[Channel_ID]": {
        "currently_mapped_to": "channel_ratings.rating_in_percent",
        "mapping_adequacy": "good",
        "description": "Rating of a channel"
      }
    },
    "constraint_bounds": {
      "Max_Time_Slots[Channel_ID]": {
        "currently_mapped_to": "missing",
        "mapping_adequacy": "missing",
        "description": "Maximum number of time slots per channel"
      },
      "Min_Local_Programs": {
        "currently_mapped_to": "missing",
        "mapping_adequacy": "missing",
        "description": "Minimum number of local programs per channel"
      }
    },
    "decision_variables": {
      "x[Channel_ID, Program_ID, Time_Slot_ID]": {
        "currently_mapped_to": "broadcast_decisions.x",
        "mapping_adequacy": "good",
        "description": "Binary decision variable indicating if a program is broadcast on a channel at a specific time",
        "variable_type": "binary"
      }
    }
  },
  "missing_optimization_requirements": [
    "Max_Time_Slots[Channel_ID]",
    "Min_Local_Programs"
  ],
  "iteration_status": {
    "complete": false,
    "confidence": "medium",
    "next_focus": "Obtain data for Max_Time_Slots[Channel_ID] and Min_Local_Programs to complete the linear formulation"
  }
}
