{
  "model_type": "movie_recommendation",
  "name": "DataSynthis_ML_JobTask",
  "description": "Movie recommendation system using collaborative filtering and matrix factorization",
  "version": "1.0.0",
  "author": "tasdid25",
  "license": "MIT",
  "framework": "scikit-learn",
  "algorithms": [
    "collaborative_filtering",
    "matrix_factorization_svd"
  ],
  "dataset": "movielens_100k",
  "features": {
    "user_id_range": [1, 943],
    "movie_count": 1682,
    "rating_count": 100000,
    "recommendation_methods": ["svd", "cf"],
    "max_recommendations": 20
  },
  "input_schema": {
    "user_id": {
      "type": "integer",
      "description": "User ID (1-943)",
      "required": true
    },
    "n_recommendations": {
      "type": "integer",
      "description": "Number of recommendations (1-20)",
      "default": 10,
      "required": false
    },
    "method": {
      "type": "string",
      "description": "Recommendation method",
      "enum": ["svd", "cf"],
      "default": "svd",
      "required": false
    }
  },
  "output_schema": {
    "type": "array",
    "items": {
      "type": "object",
      "properties": {
        "movie_id": {
          "type": "integer",
          "description": "Movie ID"
        },
        "title": {
          "type": "string",
          "description": "Movie title"
        },
        "predicted_rating": {
          "type": "number",
          "description": "Predicted rating for the user"
        }
      }
    }
  },
  "dependencies": [
    "pandas>=2.0.0",
    "numpy>=1.24.0",
    "scikit-learn>=1.3.0"
  ],
  "inference_function": "predict"
}