The problem earl.io solves

If the company deals with the coal industry (subsidiaries or suppliers), it would have negative effect on the score. More and more deals are being withheld to preserve reputation and to be saved from public backlash (Eg. Blizzard). Banks don't want to deal with companies that have bad environmental performance. They stopped trading with the Coal industry for example.

Reputational risk is definitely secondary, but it’s an emerging risk type. We tap into the local news sources, in local languages, where incidents are reported before it hits the mainstream media so that we have an early warning system. We tap into the local news sources, in local languages, where incidents are reported before it hits the mainstream media so that we have an early warning system. We maintain a database of such incidents and keep monitoring the sources for new issues so that we can alert the parties. This makes it easier to keep tabs on existing clients and do background checks on new clients so that we can ensure minimal risk!

Challenges we ran into

Open Information Extraction - Open information extraction (Open IE) refers to the extraction of relation tuples, typically binary relations, from plain text, such as (Mark Zuckerberg; founded; Facebook). The central difference from other information extraction is that the schema for these relations does not need to be specified in advance; typically the relation name is just the text linking two arguments.

For example, Barack Obama was born in Hawaii would create a triple (Barack Obama; was born in; Hawaii), corresponding to the open domain relation was-born-in(Barack-Obama, Hawaii). We had to devise a method to properly extract the relevant data.