This is a template repository to submit your Python method for the Fertility Prediction Challenge, organized by Lisa Sivak and Gert Stulp. You can read here how to participate in the challenge.
Accurate predictions of the number and timing of children are crucial for effective resource allocation in society. However, despite many studies in the social sciences, we have no clear understanding of which factors are most important for fertility prediction or how well we are able to predict fertility behaviour.
This benchmark aims to gain insight into how well methods are able to predict fertility within a three year period (2020-2022), based on survey data from previous years (2007-2019) of people in the LISS Panel who were aged 18-45 in 2019. The LISS Panel is a representative online longitudinal panel of Dutch households.
The challenge is to predict whether an individual will have a child within a three year period (2020-2022), based on survey data from previous years (2007-2019). Data about family and children, partnerships, education, income, employment, health, and more can be used for prediction.
For the SICSS-ODISSEI Summer School 2023, the challenge consists of 2 rounds. Round 1 will close on Wednesday 21 June 2023 at 16:00 and Round 2 will close on Monday 26 June at 9:00 a.m.
- Make sure you have filled out the LISS panel Data Statement form.
- Register and sign in on the Next platform using your institution email address.
- Download the example data from the challenge website (Round 1, Round 2) to tune your method:
- LISS_example_input_data.csv: data that can be used for predictions
- LISS_example_groundtruth_data.csv: contains outcome per individual (0=no child, 1=child) for training
ℹ️ This repo assumes that your method uses the Anaconda Python distribution.
- Fork and clone this repository as explained here.
- Change the content of the predict_outcomes function in script.py as explained in the script to include your method. Do not change the expected input and output data format.
- The metrics used to create the challenge leaderboards are included in this repo. You can separate the challenge example data into a train and test set and use the score function in script.py to determine your method performance scores on the example data as described here.
- Submit your method as explained here.
- Your performance scores on the challenge leaderboards will become available after signing in on the Next platform (Round 1, Round 2).
ℹ️ It takes some time to process the results for the leaderboards.
The LISS Panel challenge data is separated into an example dataset for tuning your method and a holdout dataset that will be used to validate your method performance. After submission your method will be run on the holdout data. Your performance scores on the holdout data will be added to the leaderboards, so your scores can be compared to the performance scores of other methods.
The following leaderboards will be available:
*For the prediction of having a child in 2020-2022 (positive class).
For this challenge the F1 leaderboard is the main leaderboard.
Follow the instructions below to submit your method:
- Make sure that you describe your model in the readme.md file in your GitHub repository and commit changes (i.e. save changes locally)
- Push the commit (i.e. upload changed version to your online repository)
- In GitHub make sure that the checks pass:
ℹ️ If the check fails go to FAQ, you might need to add dependencies as described here, you can also test your implementation as explained here.
- On the main page of your repository, above the file list, click commits to view a list of commits, as described here
- Go to the commit that you want to submit and right click on view commit details, then click "Copy Link Address", see example below:
- Add a submission on the Next platform (Round 1, Round 2) by providing the URL to your GitHub commit (copied at step 5), this commit will serve as your submission to the challenge.
This project is licensed under the terms of the MIT license.
The code in this repository is developed by Eyra as part of the benchmark infrastructure starter kit project funded by ODISSEI and the NWO VIDI grant awarded to Gert Stulp. The LISS panel data is provided by Centerdata.