Design team members: Dionne Schmidt and Mrugesh Desai
Supervisor: Toufic Aridi [PhD Candidate]
Background
Mobile rate plans are fixed term contracts that consumers enter into allowing for access to wireless services such as cellular calling, text messaging, internet browsing, and email. There are numerous in-market wireless providers who offer up a multitude of rate plans at varying price-points which in turn have different usage and feature allowances.
Consumers are left to select the rate plans based on what they believe to be most compatible with their usage and preferences. For example, a consumer may seek to satisfy their mobile needs through use of a smart phone such as a Blackberry and will find a rate plan that includes allowance for wireless data access so they may browse the internet and access email.
The fixed term contracts are a substantial investment on the part of the consumer and it is important for them that their rate plan is both economical and delivers the features and usage allotments they require.
Project description
The Mobile Rate Plan Optimization Model aims to match consumers with appropriate mobile rate plans based on a number of factors including usage habits based on past billing, preferences, and contract periods. Based on optimization techniques, a list of economical and compatible plans will be provided back to the user. This will save the consumer time in searching for an appropriate in-market rate plan and also ensure they are confident that they are not paying a premium for access to the wireless services they require.
Design methodology
The optimization model has been designed around the branch and bound method. Past user billing will be utilized to generate average monthly statistics with respect to usage. This will include parameters such as monthly voice minutes, roaming minutes, data usage, and international calling. New users will have to provide this data after assessing what they forecast to be their usage patterns. Preferences of the user such as the device or wireless provider they prefer will also be collected. The usage statistics and preferences will then act as constraints in a linear programming problem where the objective will be for to minimize the total cost incurred by the user. The constraints will run against a database of current in-market consumer rate plans.