{"id":20733,"date":"2022-03-18T09:55:19","date_gmt":"2022-03-18T06:55:19","guid":{"rendered":"https:\/\/quicklizard.wpenginepowered.com\/blog\/taxi-platform-case-study\/"},"modified":"2026-09-30T08:48:06","modified_gmt":"2026-09-30T05:48:06","slug":"fallstudie-zur-taxiplattform","status":"publish","type":"post","link":"https:\/\/quicklizard.com\/de\/blog\/taxi-platform-case-study\/","title":{"rendered":"Taxi-Plattform Fallstudie"},"content":{"rendered":"

The Client<\/h2>\n<\/div>\n\n\n

A United Kingdom-based taxi platform that provides customers with transportation services from a number of taxi companies. Customer log on to a website or use the company\u2019s app to order a taxi. The client is exclusively a platform and does not own or operate any taxi cabs.<\/p>\n\n\n

The Main Challenges<\/h2>\n<\/div>\n\n
\n
\n

A pure margin engagement<\/p>

Taxi prices through the taxi platform are based on two elements: the actual cost of the taxi ride and a commission. The taxi company receives payment for the taxi ride, while the taxi platform\u2019s earnings come from the commission. Like online travel agencies and other service platforms, this is a pure margin engagement.<\/p>\n<\/div> <\/article>\n

\n

The goal<\/p>

The taxi platform operates in a highly competitive marketplace, which pushes commissions down as the different players fight to maintain and grow market share. The taxi platform approached Quicklizard looking to maximize profits by finding the right commission level.<\/p>\n<\/div> <\/article>\n <\/div>\n<\/div>\n\n

The QL Solution<\/h2>\n<\/div>\n\n
    \n
  1. \n

    Real-time AI commission pricing<\/p>

    QL integrated real-time AI elements into the solution, as it designed a comprehensive dynamic pricing solution for the taxi platform. The solution set to optimize a commission based on a number of user and environmental factors.<\/p>\n<\/div> <\/li>\n

  2. \n

    Demand and user behavior analysis<\/p>

    The QL platform analyzed the effect changing levels of demand had on commission, and cross referenced it with different user behavioral actions, including user frequency, competitive price comparisons, and conversion rates.<\/p>\n<\/div> <\/li>\n

  3. \n

    Route-level recommendations<\/p>

    The platform also analyzed aggregate routes, so it could recommend a commission based on neighborhood-to-neighborhood trips rather than specific address-to-address trips.<\/p>\n<\/div> <\/li>\n <\/ol>\n<\/div>\n\n

    Das Ergebnis<\/h2>\n<\/div>\n\n