2020 Shortlist

Tiger Mum’s guide to getting your 6-year-old into the ‘right’ school

Category: Best news application

Country/area: Singapore

Organisation: Singapore Press Holdings – The Straits Times

Organisation size: Big

Publication date: 28/06/2019

Credit: Jocelyn Tan, Lee Pei Jie, Rebecca Pazos and Thong Yong Jun.

Project description:

Think it’s tough fighting for a spot in prestigious colleges? In Singapore, the competition starts at primary, or elementary, schools. The process is competitive, with many having to ballot for entry at various stages of the registration process to the most popular schools.

Based on data from the past 13 years, we build a machine learning model to predict the risk of over-subscription. And, to make it engaging for our readers, we allow them to simulate this process many times with our simulation tool.

Impact reached:

This interactive is a popular graphic, going beyond providing information to readers that would normally be conveyed in a typical article format to become a valuable, reusable widget for parents to get an idea of the chances of their child gaining entry to a school of their choice at each phase of the registration process. Engagement is high for this interactive, with average time on page reaching over 5 minutes, easily doubled the site’s average.

Techniques/technologies used:

We collect data from the past 13 years of Primary 1 registration exercises, and build a machine learning model that predicts the number of applicants by school and by phase, given the number of vacancies in that phase is known. Outcomes of this prediction (number of applicants vs vacancies) are used to determine if balloting will be required in that phase. We repeat the prediction using bootstrapping to simulate many different outcomes. For example, if in 100 simulations, 33 ended up with balloting (applicants > vacancies), the likelihood of the school going into balloting in that phase will be indicated as 33%.

What was the hardest part of this project?

We have been improving the model for this every year and it has become a mainstay for our reporting for the past two years. However, with this longevity comes the problem of keeping it relevant and interesting, especially when people have seen it in the past. This year, we went back even further and got more data to add to our machine learning for a more complete picture that aligns with the Chinese zodiac and its influence on birth patterns and cultural tendencies.

What can others learn from this project?

We think picking the right topic to do a story on is half the battle. If the story is good from the start, the execution of the idea is much easier. In this one, anything we do around Primary 1 registrations will be of interest to a large portion of our audience so this helps us in terms of reach and engagement.

Project links: