Toyota City, Japan, March 9, 2018―Toyota Motor Corporation (Toyota) and JapanTaxi Co., Ltd. (JapanTaxi), jointly with KDDI Corporation (KDDI) and Accenture, have developed a taxi dispatch support system that predicts demand for taxi services, combining data from taxi service logs with predictions of demographics made by location-based big data*1 from smartphones as well as event information. The companies have started to deploy the system in Metropolitan Tokyo on a trial basis.
The system uses artificial intelligence (AI) to predict the number of occupied taxis in Tokyo using 500-meter, mesh-based parameters every 30 minutes. The companies collect taxi service log data and demographic predictions as well as other factors that affect taxi demand such as weather, public transport service availability, and events at large facilities, and apply learning models through an AI-based system to predict the size of demand. In a test run in Tokyo, the system demonstrated a high accuracy rate of 94.1 percent.
Since February 2018 the companies have been piloting the system with select taxis of Nihon Kotsu Co., Ltd., affiliate company of JapanTaxi, using tablet PCs equipped with the system. A map on the tablet shows not only the predicted number of occupied taxis but the latest number of unoccupied taxis around the area, which allows drivers to position their taxis based on the supply-demand balance. As a result, more taxis can serve areas with higher demand and insufficient supply to reduce waiting time for passengers while taxi occupancy rate is increased with optimal vehicle-dispatch. In addition, drivers can receive supporting information on the tablet that shows the routes where they are likely to find passengers, based on insights of excellent drivers.
During the pilot, drivers who used the system recorded an average sales increase of 20.4 percent in February 2018 on a month-to-month basis, compared to an overall average increase of 9.4 percent. Dozens more taxis will trial the system with an aim to roll it out for widespread use later in the year.
The companies believe that the system can contribute to transforming the taxi industry, enhancing convenience while also being used as a training tool for new taxi drivers. The companies plan to research the correlations between an analysis of driving image collected from Toyota's data-transmission TransLog driving recorder of which installation on taxis will be steadily expanded and taxi demand to leverage for the system, and further develop the system to help create a seamless mobility experience.
Role of Each Company
- Process and analyze collected big data on its Mobility Services Platform (MSPF), and provide JapanTaxi with taxi demand prediction data.
- Collect data affecting taxi demand such as weather, public transport service availability, and events at large facilities.
- Develop app that offers taxi demand prediction data to taxi drivers.
- Collect and offer taxi service log, positional information of unoccupied taxis, and routes on which drivers are likely to find passengers via a taxi company.
- Develop a demographic prediction technology that considers people flow such as those moving and staying using KDDI's location-based big data from smartphones and provide prediction data.
- Jointly define requirements with the three other companies and develop the analytics algorithm of artificial intelligence that powers the taxi demand prediction engine.
*1The location-based big data is anonymized and provided upon obtaining au smartphone users' agreement.
Japan Taxi is an IT business venture that develops software and hardware for mobility services.
Japan Taxi aims to "provide happiness through transport" by creating new public transportation infrastructure through the most widely used domestic taxi app, Zenkoku Taxi, digital ads in taxi interiors provided by "TOKYO PRIME," and tablet computers featuring multilingual services and a point of sale terminal.
Zenkoku Taxi has been downloaded more than 4 million times (as of December 2017) and is the most widely used domestic taxi dispatch service app.
The network covers 47 prefectures and 60,000 taxis, which amounts to 25 percent of domestic taxis.
The service is available in three languages (English, Chinese, and Korean), can estimate taxi fares, accepts cashless payment through credit cards and QR codes, and contributes to increased efficiency and convenient usage for taxis.