In Progress
00

day

00

hr

00

min

00

sec

Time to deadline

Topic provider

Taiwan Taxi, founded in September, 2005, is the largest taxi company in Taiwan. The company serves around 350,000 customers through the taxi dispatching platform receiving more than 120,000 hotlines per day. The company provides taxi service around the island with running more than 10,000 taxies, accounting for 19% in taxi industry in Taiwan. The company has been deeply trusted by customers and has been awarded 『Excellent』of Taipei Taxi Transportation Service in consecutive 7 years by the overwhelming numbers of taxi than competitors with the good image of brand. Over the recent years, the company has also equipped with diversified services and aggressively been cooperated with horizontal alliances to build the best brand of taxi service for customers.

Introduction


The purpose of passenger hotspots prediction is to predict a location and time based passenger demand based on the analyzed historical data. By adopting a proper prediction model, load factors of taxis can increase, passenger waiting time can be lower, moreover, the amount of empty taxis and their exhaust emissions can decrease and thus the quality of transportation services can be improved. The prediction can also be considered a significant reference to manage or develop an intelligent city

This is a limited-participation topic. Only the students that take Professor Hsueh-Ting Chu's 2020 summer program may participate.

Activity time

This project ends at 23:59:59 on 08/25/2020., with its Private Leaderboard being announced at 00:00:00 on 01/09/2020.

Evaluation Criteria


After the forecasts of the passenger demand number is provided, the system would calculate the score based on the evaluation criteria.Evaluations are conducted by calculating the Root-Mean-Square Error, RMSE, of the actual value. The formula is as follows: $$RMSE = \sqrt{{1 \over n} \sum_{j=1}^{n} (y_i - \hat{y}_i) ^ 2}$$

Rules

  • The evaluation result would be based on the final result. If two teams (or more) got the same evaluation scores, the time they upload would determine the ranking.
  • If there is cheating or fraud during the activity, the team that cheats will be disqualified from the activity and the vacancy would be filled up by other teams in the ranking order.
  • Using external data sets that are legally authorized is allowed. However, to assess the fairness, data sets instructions and references should be stated in the forum for references.
  • After uploading, the answers of test data would be divided into two parts to calculate the score:
    • Before the deadline of the activity: The system refers to only a part of the test data to examine and calculate the score. The result will be posted on the Public Leaderboard as reference for the final score and ranking. This data accounts for 60% of the entire test data.
    • After the deadline of the activity: The system refers to the remaining test data (40%) to examine and calculate the score. The result will be posted on the Public Leaderboard as reference for the final score and ranking.