Application of Mean Shift Clustering to optimize matching problems in ridesharing for maximize the total number of match

The ridesharing system One of the solution can reduce the use of private vehicles so as to reduce congestion. The problem that happened with this ridesharing system is the matching problem between the driver and the passenger (rider). Mean shift clustering will be used in this paper as the first step in optimizing the matching problem in ridesharing. Mean shift clustering is a method of grouping spatial data by iteratively assigning data points to groups by shifting points to mode (mode is the highest density of data points in the region, in the context of mean-shift). So that with clustering it will be easier and more effective in pairing drivers and passengers optimally. After the clustering results are obtained, the driver and passenger will be paired based on the objective function of maximizing the number of pairs that occur (match). The basic idea of this objective function is to find the maximum number of match to do ridesharing. With the help of the Hopcroft Karp algorithm, can find a solution for the maximum number of match to do ridesharing.