{
  "id": "1511.01853",
  "version": "v1",
  "published": "2015-11-05T19:09:25.000Z",
  "updated": "2015-11-05T19:09:25.000Z",
  "title": "Autoregressive Model for Individual Consumption Data - LASSO Selection and Significance Test",
  "authors": [
    "Pan Li",
    "Baosen Zhang",
    "Yang Weng",
    "Ram Rajagopal"
  ],
  "comment": "21 pages, 5 figures",
  "categories": [
    "stat.ML",
    "cs.SY",
    "math.OC"
  ],
  "abstract": "Understanding user flexibility and behavior patterns is becoming increasingly vital to the design of robust and efficient energy saving programs. Accurate prediction of consumption is a key part to this understanding. Existing prediction methods usually have high relative errors that can be larger than 30\\%. In this paper, we explore sparsity in users' past data and relationship between different users to increase prediction accuracy. We show that using LASSO and significance test techniques, prediction accuracy can be significantly compared to standard existing algorithms. We use mean absolute percentage error (MAPE) as the criteria.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2015-11-05T19:09:25.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "individual consumption data",
      "lasso selection",
      "autoregressive model",
      "mean absolute percentage error",
      "efficient energy saving programs"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 21,
      "language": "en",
      "license": "arXiv",
      "status": "editable",
      "adsabs": "2015arXiv151101853L"
    }
  }
}