This is a Kaggle competition set up for Question 1 of CodeBoss 2020. A maximum number of 10 submissions are allowed for each team.

**The Challenge**

Given Bitcoin transaction graph data, predict which ransomware family a Bitcoin address belongs to.

**The Story**

Ransomware attacks encrypts sensitive information to exchange for a ransom. Attacks have been shown by studies to have caused significant economic losses and the usage of cryptocurrencies like Bitcoin have made it easier for ransomware developers to attack.

Bitcoin transaction data are permanently recorded and publicly available. However, current methods to detect ransomware relies only on a couple of heuristics. The idea of exploring data modelling techniques is not widespread as of now.

This challenge proposes to use data modelling techniques for a data driven method to detect new Bitcoin address from a ransomware family.

**What Data Will I Use in This Competition?**

In this competition, you will have access to two similar datasets that include attributes and labels. One dataset is titled `train.csv` and the other is titled `test.csv`. The datasets are anonymized.
Each of these train and test have the same features, and only the train.csv file will include the correct labels, being the ransomware family.

You will have to model the train data, to the best of your ability and predict the corresponding labels in the test data. 

Check out the “Data” tab to explore the datasets even further. Once you feel you have created a competitive model, submit it to see where your model stands on our leader board against other contestants.

**Tips**

While the score your model achieves is the most important factor in determining the Kaggle ranking, if two models achieves the same results, the earlier submission will rank higher!
A tip from us is to do a quick baseline and submit periodically after improvements to the model. Use your 10 submissions well!