Challenge 20.1

Challenge 20.1 – Using machine learning to predict Active vs Inactive customers

TracFone’s customers draw from diverse and vibrant backgrounds. For example, they may be proudly pragmatic who appreciate good value mobile service plans. Alternatively, they may be travelers that are temporarily visiting friends or family or forming new memories on their vacation to take home with them. They may even belong to financially fragile communities that have traditionally been underserved by the large wireless providers that required credit and long-term contracts. Ever since our inception in 1996, our focus has always been on providing Coverage And Access For All

In the prepaid cellular service market that we pioneered in the USA, customers pay for service in advance of the month with no contracts or obligations to continue their service the following month. This gives our customers tremendous flexibility to manage their monthly spending and adapt to their shifting circumstances. They may continue to prepay the same amount for next month’s service, change to a different service plan, or let their service become Inactive.

A service going inactive may be expected for a customer temporarily visiting the USA. Meanwhile, financially fragile members of our community may become inactive for the month and later return with necessary funds to activate their service. An economically secure customer may choose to move to another one of TracFone’s other ten brands, or leave TracFone all together. 

One of the challenges data scientists in TracFone contend with is predicting if a customer is likely to become inactive. Accurately predicting a customer’s future Active vs Inactive status allows us to recommend appropriate ways for them to continue their service. After all, cellular service is a necessary part of our modern lifestyle, and we want to do our best to keep our customers connected.

Can you build a model to predict if a service will continue to remain Active or become Inactive in two weeks?


1st Place Team: SparkNan Zhou, Junlin Wu, Xiaoli Han, Linyi Du & Wenhan Sun

2nd Place Team: DuduQingdu Meng, Fanyi Zhang, Jingwen Huang & Kexin Jing

3rd Place Team: LatamJose D Apollo, Asher Ginsburg, Juan Castano & Fernando Solorzano

Who can join in?

TracHack 20.1 participants will be students enrolled in the Master of Science in Business Analytics (MSBA) in A/Prof Daniel McGibney’s class. We hope to expand the participation in subsequent challenges (i.e. 20.2, 20.3, etc ). Drop us an email if you couldn’t participate this time and would want to participate in the next event.

When, where and how long?

TracHack 20.1 starts on April 8, 2020 and ends May 3, 2020. The teams will make three submissions of their solutions. Each submission will be scored and teams will be ranked by the AUC metric for leaderboard positions.

The winners of the challenge will be announced based on the ranking from the final submission. The top three teams with the highest AUC score will win cash prizes, fame and glory.

Even though the final ranking is based on the final submission, it is a good idea to validate the approach and solution along the way using each of the submission deadlines as checkpoints.

What happens when my team wins?

You win fame, glory and bragging rights. There are also cash prizes for the teams to go with trophies:

1st place team: $3,000

2nd place team: $2,000

3rd place team: $1,000

The winning teams will be required to make a 10-minute presentation at the award ceremony that describes their solution and how they tackled this problem.

How do I get started?

  • Understand the Rules and consult the FAQ.
  • Join a team (if not already) – Check with A/Prof Daniel McGibney.
  • Sign an NDA on data usage – If you are part of a signed up team you would have gotten a DocuSign email.
  • Ensure you are set up to make your Submissions – Check your email for an invitation for Atlassian/BitBucket.
  • Set up to make your Submissions.
  • Download the data – Once you have signed the NDA you will get an email with the link to where you can download the data.

Key dates

April 8, 2020TracHack 20.1 KickOff
April 15, 2020 – 11:59pm US ETFirst submission
April 22, 2020 – 11:59pm US ETSecond submission
May 3, 2020 – 11:59pm US ETFinal submission ****
May 8, 2020Awards & Presentations


If you have any questions, feel free to reach out to us at