# What is Forta?

[Forta](https://forta.org/) is a real-time detection network for security & operational monitoring of blockchain activity
As a decentralized monitoring network, Forta detects threats and anomalies on DeFi, NFT, governance, bridges, and other Web3 systems in real-time to protect the web3 ecosystem.

[![Forta Intro Youtube Video](https://user-images.githubusercontent.com/3497137/188163437-70d0ae07-ce0c-4840-aad8-08612bcaf211.gif)](https://www.youtube.com/watch?v=FNj_Kqc3fe8)

[Forta Blog Post introducing this competition](https://forta.org/blog/predicting-phishing-kaggle/)

[Watch a 2-minute clip on how Forta protects Web3](https://www.youtube.com/watch?v=FNj_Kqc3fe8)

# Problem Statement

Chainalysis estimated scam losses of 7.7 billion dollars for 2021 in [their 2022 cyber crime report](https://go.chainalysis.com/2022-Crypto-Crime-Report.html). In August alone, [Web3Rekt](https://www.web3rekt.com/) recorded 34 scams, targeting web3 users ranging from NFT owners to De-Fi users. The owners of [NFT: Bored Ape Yacht Club](https://opensea.io/collection/boredapeyachtclub) fell victim to a scam (see [New BAYC Owner Scammed Just Two Hours After Purchasing $116K NFT
](https://beincrypto.com/new-bayc-owner-scammed-just-two-hours-after-purchasing-116k-nft) ). On August 9th, 2022, Curve Finance users were tricked into token approvals, and their wallets were quickly drained (see [Curve Finance Rekt](https://rekt.news/curve-finance-rekt/)).

These attacks are commonly referred to as [ice phishing attacks](https://forta.org/blog/how-to-derail-a-120-million-dollar-hack/). On the Forta Network, there is a heuristic-based bot that attempts to identify these ice phishing attacks (see [Ice Phishing 2.0 bot](https://explorer.forta.network/bot/0x8badbf2ad65abc3df5b1d9cc388e419d9255ef999fb69aac6bf395646cf01c14)). However, the bot emits false positive alerts, identifying many approval events that are not part of an actual scam.

Machine learning can surface potential threats with high confidence and reduce most false alarms often seen in heuristic based systems. For example, ML can detect future phishing activity by analyzing past phishing attacks and transaction flow. The authors of a research paper: [“Who Are the Phishers?“](https://arxiv.org/abs/1911.09259) gathered phishing related labels from [Etherscan](https://etherscan.io/accounts/label/phish-hack) and [CryptoScamDB](https://github.com/CryptoScamDB/EtherScamDB), and created a ML solution that detects phishing attacks with 92.7% precision and 89.3% recall. A ML model like this can be deployed in a [Forta detection bot](https://docs.forta.network/en/latest/getting-started/). Block by block or for every incoming transaction, the bot can invoke the model to predict if any addresses are involved in a phishing attack. 

# Objective

Your goal is to develop a machine learning model that can accurately predict if an Ethereum Externally Owned Account (EOA) is a phishing scammer. For each `Id` in the test set, your task is to predict the value of the `target`: 0 for benign EOAs, 1 for phishing scammers. 

The training set includes a random sample of unlabelled EOAs and a small sample (<1%) of EOAs involved in phishing scams. The labels were derived from addresses labeled with `phish/hack` on [Etherscan](https://etherscan.io/accounts/label/phish-hack). 

We provided train/test EOA transactions, traces, logs, and even statistics on one-degree neighbors' transactions for a given timeframe. The data is time-sliced in the following way:

-  Train transactions and metadata executed before January 16, 2022. 
-  Test transactions and metadata executed before July 18, 2022.

You are free to use all or some of the provided data. We also provided additional data sources you can tap into in the [Tutorial and Resources section](https://www.kaggle.com/competitions/forta-protect-web3/overview/tutorials-and-resources).