# AI Against Modern Slavery - TWIML Hackathon — Data

来源：https://www.kaggle.com/competitions/ai-against-modern-slavery-twiml-competition/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

There are two files that you need:

- **train.csv** - containing the 650 examples of training data
- **test.csv** - containing the 331 examples of competition data, with the LABELs that you need to predict.

The sample_submission.csv is an example of correctly formatted submission file.

The training data contains the extracted texts from companies' modern slavery statements. These statements are originally published in PDF (both scanned and digital) and HTML formats. A variety of methods has been used to get the raw text including OCR and HTML scraping techniques which is why sometimes you might see some noise or misaligned titles.

The target metric LABEL_MSA_training_binary essentially answers the question: Does the company provide training specifically to address modern slavery and human trafficking? 

This training can take place as a standalone course on modern slavery, or be embedded in a wider training programme on supply chains or human rights. It can cover many different groups- procurement specialists, and those who work in recruitment or in leadership positions.

Training can be provided to:
- Employees (all)
- Procurement / purchasing
- Recruitment / HR
- Leadership
- Suppliers

The train.csv includes the ground truth 1/0 values for each statement and your task is to estimate the probability for all the documents in the test set whether they contain information about the provision of training.

It's possible that the statement mentions the provision of training but:
a) it's not specified to whom or about what, or;
b) some training methodology is only being created, that is, it's "in development"
in those instances the target value is 0 because companies can provide any types of training while we care about specifically modern slavery related training programs. Additionally, training programs that are in development are not creating any impactful change in the world.