Do you know what Natural Language Processing (NLP) is? If you don't and you want to remain working in a front office job in an investment bank in future, you'd better familiarize yourself with the term soon.
1. NLP is the new-new thing in banking
Banks know that their traders spend lot of time reading about markets, that compliance teams need to read internal communications to identify wrongdoing by market participants, and that salespeople continually keep track of numerous chats with their clients.
To succeed in a bank, you need to read. The problem is that there’s never enough time to read everything. - It takes time to sort through the noise to to valuable nuggets information and often you can miss them. Wouldn’t it be great, therefore, if all this reading could be automated? - And not just reading. - If listening to earnings calls could be automated, and if articles could be automatically generated after common market events?
NLP seeks to do all of the above, and more. And banks are waking up to its potential. For example, Goldman Sachs' Charles Elkan says the bank is using NLP to read through all its contracts. Both Goldman Sachs and JPMorgan are looking for NLP specialists to work on their internal search engines.
2. NLP has its own vernacular
Understanding NLP means knowing the difference between morphology, syntax, semantics and pragmatics.
Morphology looks at how words themselves are constructed. For example, words like eat, ate and eating share a common root. Syntax then analyses how words fit together in a sentence in a grammatically correct way. - “Alex consumes burgers” and “Burgers consume Alex” have nearly identical words, but the word order changes how we interpret the sentence.
Semantics is about structuring the information so that we can ask questions about the text like, 'Who, what, or where?' For example, we might have a word cloud about a particular stock that allows us to analyze the sentiment of the text.
Pragmatics is where we seek an overall understanding of a text - often by referring to sources outside of it.
3. Open-source NLP Python libraries will help you get started
If you're a technologist, getting started with NLP might sound like a huge headache. It needn't be. You can buy things like newsire text databases, where the structuring and cleaning of text has happened already. And if you use Python there are a lot of great NLP open source packages that will do these tasks for you. - The best known is Natural Language Toolkit (NLTK), but there are others like spaCy too.
These open source packages will do a lot of NLP tasks for you - ranging from word segmentation to part-of-speech tagging to sentiment analysis. There are also tools like Beautiful Soup that will clean up text for you. Many cloud providers also offer their own NLP services which can be used to structure and interpret text.
It takes time to get your head around NLP! However, it’s worthwhile and if you can learn it now you'll have a headstart in finance jobs of the future.
Saeed Amen is the founder of Cuemacro. Over the past decade and a half, Saeed Amen has developed systematic trading strategies at major investment banks including Lehman Brothers and Nomura. He is the author of Trading Thalesians: What the ancient world can teach us about trading today (Palgrave Macmillan) and is currently co-authoring The Book of Alternative Data (Wiley) with Alex Denev. Through Cuemacro, he now consults and publishes research for clients in the area of systematic trading. He has developed many Python libraries including finmarketpy and tcapy for transaction cost analysis. His clients have included major quant funds and data companies such as Bloomberg. He has presented his research at many conferences and institutions including the ECB and the Fed. He is also a co-founder of the Thalesians.
Have a confidential story, tip, or comment you’d like to share? Contact: firstname.lastname@example.org in the first instance. Whatsapp/Signal/Telegram also available.
Bear with us if you leave a comment at the bottom of this article: all our comments are moderated by human beings. Sometimes these humans might be asleep, or away from their desks, so it may take a while for your comment to appear. Eventually it will – unless it’s offensive or libelous (in which case it won’t.)