METHOD AND APPARATUS FOR PROVIDING MODEL SELECTION FOR TRAFFIC PREDICTION

摘要

An approach is provided for determining one or more real-time traffic data series associated with one or more road segments over one or more time intervals. The approach involves causing, at least in part, a determination of one or more differences of the real-time data series with one or more historical models. The approach also involves determining whether the one or more real-time difference exceeds a threshold difference. The approach involves causing, at least in part, a selection of one or more other historical models for the one or more road segments over the one or more time intervals based, at least in part, on a determination that the real-time difference exceeds the threshold difference.

主权项

1. A method comprising:
determining at least one first model and at least one second model, wherein the at least one first model and the at least one second model provide for predicting traffic information for one or more travel segments; determining at least one first confidence metric by evaluating the at least one first model against real-time traffic data associated with the one or more travel segments, wherein the real-time traffic data are collected over a predetermined previous time period; determining at least one second confidence metric by evaluating the at least one second model against the real-time traffic data; causing, at least in part, a selection of at least one champion model from among the at least one first model and the at least one second model based, at least in part, on the at least one first confidence metric and the at least one second confidence metric, wherein the least one champion model is used to predict the traffic information for the one or more travel segments based, at least in part, on the selection.