Student Forecasting Tournament

Bring Decision Education to your High School Classroom with Forecasting—and Win Cash Prizes!

Student Teams Enter Multiple Forecasts Over Ten Weeks

The Alliance for Decision Education and Good Judgment are teaming up to offer the Student Forecasting Tournament, an exciting, gamified learning opportunity for high school students to discover how to make predictions about future events and improve their decision-making skills.

In this online tournament, students work together in teams of four to submit their own forecasts to various questions about current, real-world events.

After ten weeks, the teams with the most correct predictions and the highest level of accuracy win cash prizes!

Tournament Structure

The Student Forecasting Tournament is a ten-week online tournament open to all US-based teachers and their high school students. To get started, teachers pre-register themselves and confirm eligibility. Teachers then register student teams made up of four students. Each teacher must register a minimum of two teams, and are welcome to register additional teams.

The tournament is made up of five, two-week rounds. For each round, five questions are released and students are challenged to predict the outcome for each question, provide their rationale, and make their best estimation at the probability that the event will or won’t occur.

During each round, teachers use a modest amount of class time to teach forecasting concepts, foster discussion, review leaderboards, and provide students with time to collaborate with their team. Each student inputs their own forecast into the private, online forecasting platform and receives a Brier score. A team’s score is the average of all four team members’ individual Brier scores.

Throughout the tournament, prizes are given out each round to the top three teams on the leaderboard. Team ranking is based on the team’s score. In order to qualify for top cash prizes, teams need to submit forecasts for 100% of the questions.

Tournament Details

Prizes

  • 1st place:
    • $2,500 school cash prize made out to the school
    • $500 scholarship for each of the students on the winning team
  • 2nd place:
    •  $1,500 school cash prize made out to the school
    • $500 scholarship for each of the students on the winning team
  • 3rd place:
    •  $1,000 school cash prize made out to the school
    • $500 scholarship for each of the students on the winning team
  • Round Winners
    • Every round, the teachers of the top three teams on the leaderboard will receive $100 Amazon gift cards.
  • Student Participation Prizes
    • $100 Amazon gift cards for all individual students who complete 100% of the tournament by predicting each question over the ten weeks.

Important Dates

  • December 7, 2022
    • Teacher registration opens
  • January 10, 2023
    • Teacher registration closes 
  • January 10, 2023
    • Last day for teachers to register student teams
  • February 6, 2023
    • Tournament begins
  • April 14, 2023
    • Tournament ends and winners are announced

Frequently Asked Questions

Using current events, students learn the skills to test, bring to life, and sharpen their decision-making skills. When they learn how to predict the outcome of future events, they learn to explore an evolving world in a structured way—developing the skills and dispositions to update their beliefs based on new information. Forecasting provides a gamified way for students to engage with Decision Education—and it’s fun!

Updating is an important part of the forecasting process. As students receive new information regarding a question posed, they  are encouraged to revisit their predictions and update them as they see fit. For example, a student team originally predicted that an AFC team would win the Super Bowl, but a week later the top two NFL teams in the AFC were knocked out during the playoffs. The student team now has new information and may want to “update” their initial prediction or confidence in their prediction.

Simply put, the questions within this tournament can be answered with a “yes” or “no” response; however, the power of forecasting exists within the predictor’s confidence in their answer. Example questions could be: “Will the winner of Super Bowl LVII be an AFC team?” Or “Will TikTok enact mandatory time and content restrictions for American children under 18?” Not only will the student have to answer “yes” or “no,” but they will have to provide a rationale and account for how confident they are using a confidence interval. Students are encouraged to revisit their predictions during each round and adjust as new information becomes available.

The tournament will consist of five two-week rounds, with five questions in each round (25 total questions). The questions will be posted and active within the tournament platform on the first day of each round. The questions will remain active throughout each two-week round.

We are partnering with Good Judgment, Inc., and the tournament is run on their forecasting platform, which is a secure, web-based application where students will log in to submit their predictions. Within the platform, students will predict outcomes to the given questions, write a short rationale for their predictions, and engage with their teammates. Students can see their individual and team ranking on the tournament leaderboard at all times on the platform. 

Teachers will serve as administrators for their student teams within the platform—they will ensure that students are able to log in, but the role of teachers will also include monitoring progress. They will be able to see their students’ entries, comment, and pose questions to their students to encourage ongoing engagement.

Students need to be able to access and use a web browser. The platform will require each student to log in with an (anonymized) username and password, write within text fields, and use a sliding scale in order to display how confident they are with their answer.

The tournament is open to all US-based high school classroom teachers who teach a core subject, and their high school students (grades 9-12).

We expect that teachers and students will spend roughly 45-60 minutes per week involved in their forecasting activities—most likely a combo of at-home and in-class time. In the early weeks of the tournament, teachers will likely facilitate more instruction and guided conversations regarding forecasting. As the tournament progresses, teachers and students may find that their time is best used in research, discussion, and/or analysis. 

Teachers will decide the flow of class time that works best for them, but in general we imagine that when each round of questions are posted, teachers will dedicate some class time for students to talk about the questions, work within their teams on their forecasts, and perhaps update their earlier predictions based on any new information that they have.

Teachers will complete a forecasting webinar that is designed to provide a basic understanding of the concepts of Decision Education and how they apply to forecasting. The webinar will also cover necessary information for teachers regarding the tournament platform, the format of the tournament, and resources for classroom instruction. Teachers will also have access to a community platform, forecasting coaches, tech support, etc. 

The Brier score was originally proposed to quantify the accuracy of weather forecasts, but can be used to describe the accuracy of any probabilistic forecast. Roughly, the Brier score indicates how far away from the truth your forecast was.

The Brier score is the squared error of a probabilistic forecast. To calculate it, we divide your forecast by 100 so that your probabilities range between 0 (0%) and 1 (100%). Then, we code reality as either 0 (if the event did not happen) or 1 (if the event did happen). For each answer option, we take the difference between your forecast and the correct answer, square the differences, and add them all together. 

For example: For a yes/no question where you forecasted 70% and the event happened, your score would be (1 – 0.7)² + (0 – 0.3)² = 0.18. For a question with three possible outcomes (A, B, C) where you forecasted A = 60%, B = 10%, C = 30% and A occurred, your score would be (1 – 0.6)² + (0 – 0.1)² + (0 – 0.3)² = 0.26. The best (lowest) possible Brier score is 0, and the worst (highest) possible Brier score is 2.

The top three student teams with the lowest Brier score (most correct predictions with the highest level of confidence) win.  We will send all teachers an analysis of their students’ forecasting data at the end of the tournament.

Each of the students from the top three winning teams will receive a scholarship check for $500 sent directly to their families.  

The teachers of the top three winning teams will each receive a classroom award check made out to/sent directly to the school. The funds are to be used for instructional purposes. See the prize chart above for exact amounts.

Round leader prizes and the participation prizes are Amazon gift cards and will be sent electronically.  

It is required that teachers request permission from their schools in order to have students participate in the tournament. Please check with your school and/or district regarding student participation in online competitions.

We will collect:

  • Student forecast data submitted on the tournament platform. We won’t collect any personal information from students and all forecasting data will be anonymized.
  • Teacher and student survey data, with the purpose of finding out what students learned through the Forecasting Tournament. This will provide feedback on their experience with the platform and the tournament as a whole.

We will send all teachers an analysis of their students’ forecasting data at the end of the tournament.

Please contact us at david@alliancefordecisioneducation.org.

Stay informed and join our mailing list

We will send you occasional updates on the organization. Your information will not be sold or otherwise distributed.