{
  "id": "1812.03699",
  "version": "v1",
  "published": "2018-12-10T09:53:04.000Z",
  "updated": "2018-12-10T09:53:04.000Z",
  "title": "Taxi Demand-Supply Forecasting: Impact of Spatial Partitioning on the Performance of Neural Networks",
  "authors": [
    "Neema Davis",
    "Gaurav Raina",
    "Krishna Jagannathan"
  ],
  "comment": "Presented at the NIPS Workshop on Machine Learning in Intelligent Transportation Systems, 2018",
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "In this paper, we investigate the significance of choosing an appropriate tessellation strategy for a spatio-temporal taxi demand-supply modeling framework. Our study compares (i) the variable-sized polygon based Voronoi tessellation, and (ii) the fixed-sized grid based Geohash tessellation, using taxi demand-supply GPS data for the cities of Bengaluru, India and New York, USA. Long Short-Term Memory (LSTM) networks are used for modeling and incorporating information from spatial neighbors into the model. We find that the LSTM model based on input features extracted from a variable-sized polygon tessellation yields superior performance over the LSTM model based on fixed-sized grid tessellation. Our study highlights the need to explore multiple spatial partitioning techniques for improving the prediction performance in neural network models.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-12-10T09:53:04.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "neural network",
      "taxi demand-supply forecasting",
      "spatial partitioning",
      "taxi demand-supply modeling framework",
      "polygon tessellation yields superior performance"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}