Welcome to the TWIMLfest AI for Good Hackathon!
Contribute to Modern Slavery Research
In 2018, the Global Slavery Index found that there were 40.3 M people in modern slavery, of whom 25M were in forced labor producing computers, clothing, agricultural products, raw materials, etc and 15M were in forced marriage. In order to facilitate measures to end modern slavery the United Nations asks companies to take immediate measures and state clear policies. The Future Society is an independent nonprofit think-and-do tank curating an up-to-date repository of >16K of those statements. Use your NLP-Skills predict whether those statements meet the required standards!
The data for this competition consists of 981 of those statements from different companies with an expert-reviewed annotation. This annotation is used to determine whether the company is providing training to their employees and supply chain workers regarding addressing modern slavery and human trafficking. Training can be provided to
Employees (all)
Procurement / purchasing
Recruitment / HR
Leadership
Suppliers
or it might not be mentioned who exactly
You can use any NLP-Method on the text of those statements and try to predict if the training is sufficiently addressed or not.
Evaluation
From the 981 data points of the data set 288 are used for evaluating your models. These 288 statements are evenly split into a public and a private leaderboard. For this binary classification problem we're evaluating with binary cross entropy/ logloss:
\[
\text{score} = - \frac{1}{N}\sum_{i=1}^{N} \left[ y_{i} \log(\hat{y}_{i}) + (1 - y_{i}) \log(1 - \hat{y}_{i})\right]
\]
Submission Format
Your task is to provide
probability estimates (NOT final classifications)
for the test set whether they classify as "Training Provided" or not. All statements in the test set have a unique ID. The predictions on the statements of the test set should be submitted in the following format as a comma separated csv file:
ID, LABEL_MSA_training_binary
1, 0.0
2, 0.0
3, 0.0
...
Timeline
The hackathon starts on Wednesday, October 14th after the introduction session and we will finish on Wednesday, October 28th at 4:30 PM CEST (Register
[here](https://twimlai.com/twimlfest/sessions/ai-for-good-hackathon-end-modern-slavery/)
). During TWIMLfest we will have a weekly checking, you can find the dates
[here](https://twimlai.com/twimlfest/sessions/ai-for-good-hackathon-end-modern-slavery/)
.
Prizes and Karma
This Hackathon is intended to help the global research community improve their work on screening Modern Slavery Statements to hold global corporations accountable. As a small incentive there will be the following prizes:
1. Place: $250
2. Place: $100
3. Place: $50
The Prizes can be taken as credit for your favourite cloud provider or as a credit for TWIML swag.
You are not allowed to use external data sources for this competition than what is provided through this page. Your solution should also be able to scale over tens of thousands of modern slavery statements so manually reading and classifying the statements does not qualify here. We ask you to be fair and not cheat. Cheating at an AI for Good Hackathon probably brings some pretty bad karma :-) As a winner you should be prepared to showcase your approach, share your code so it can be reproduced!