NLP & The Financial Sector
There’s more than one meaning for NLP, which you might encounter. If you Google it, one of these is Neuro Linguistic Programming, and techniques of communicating with other folks. Well this post is absolutely nothing to do that! Instead, it’s to do with the NLP, which occupies more of my time, natural language processing.
In a nutshell, it’s about trying to do the types of tasks that humans undertake when dealing with a “real” language, with a computer.
Sometimes this can involve writing, ie. natural language generation.
This could be related to tasks such as creating chatbots. For a financial firm, these chatbots could be programmed to interact with clients, such as on a market making desk, whether that’s answering questions about markets or executing orders.
In practice, for investors, natural language generation is probably less important than it would be for the sell side. Instead, for those seeking to generate “alpha”, natural language understanding is more important, in other words making sense of text.
The idea of using text to trade markets isn’t really new. News for one has always been a big mover of markets, and I doubt many would disagree with that. The difficulty is that there is so much text being generated that could impact markets, is that it is impossible for a human to read it all.
With machines to help us read the news, we can read text from many sources, be it from newswires, social media and the web more broadly.
The next question is what can NLP help us do? It can help us to structure text, to add tags to texts to make them easier for us to understand. These can range from the timestamp, to understanding which topics a text is about and pretty key, what tradable ticker could be impacted by text.
Other important tags include understanding the sentiment associated with a text, how novel that text could, the amount of readership a text has got etc. Once we have structured a text, we can then construct all sorts of things, such as indicators or decipher which types of topics are being discussed the most etc.
The key question with NLP is how much work you want to do versus a vendor? I would argue that particularly when you begin to tackle NLP, having a vendor to do a lot of the heavy lifting is helpful. Yes you can try to do a lot of the “tagging” yourself, but in many cases, a vendor can do it quicker and cheaper.
This is particularly the case if you don’t have access to a massive quant team with NLP experts. There are also open source tools too for NLP. I’d also say that in some areas, such as macro, NLP hasn’t really been used quite so much, and it isn’t too late to start if you’re an investor who wants to use it. If you’re interested in NLP, take a look at The Book of Alternative Data, which Alexander Denev and I wrote as well!
NLP & The Financial Sector Written by Saeed Amen
Over the past 15 years, I have developed algorithmic trading strategies at Lehman Brothers (where I co-developed MarQCuS which had $2bn AUM), Nomura, the Thalesians and Cuemacro. I am the founder of Cuemacro and the co-founder of Thalesians. I have profitably run systematic trading models for market making trading desks. Clients have included Bloomberg, Accenture, CLS, Freepoint Commodities, RavenPack, Cytora, Investopedia, a Chicago prop firm, a large European asset manager and several UK quant hedge funds.
TCA – Cuemacro have developed a Python based FX TCA library, tcapy, a fully open source library. Hundreds of K cheaper than developing your own library!
Research Consulting – Cuemacro provides extensive consulting services across currency, fixed income & equities markets, to create bespoke systematic trading models and deliver quant analysis of markets. Our expertise includes FX hedging, transaction cost analysis (TCA), vol trading models, macro based trading indicators and alternative data based trading strategies.
Data Products – Cuemacro publish data indices to map economic sentiment, such as our Fed sentiment index, using both common and unusual datasets for macro trading, drawing on our expertise in alternative data, as well as trading indices.
Monetising Data – Cuemacro can help your firm, whether it is a data, corporate or financial firm, understand how to monetise your datasets and how to use data more effectively internally. We can create a comprehensive data strategy for your firm.
Books – Trading Thalesians – What the ancient world can teach about trading today (Palgrave Macmillan) – Saeed Amen
– The Book of Alternative Data (Wiley) – Alexander Denev & Saeed Amen
I have presented many conferences like QuantMinds, as well at ECB, Federal Reserve Board, IMF and Bank of England. If you are interested in Cuemacro’s products and services, please contact me.
Saeed published this article originally for his firm:
Seeking the cues in macro markets
What are the signals we can use to trade macro markets? Cuemacro is a company focused on understanding macro markets from a quantitative perspective, in particular currency markets. Our goal is understand how data can be used to deepen understanding of macro markets. We use both existing and innovative data sources to create systematic trading strategies, analytics and data indices. We build our analytics using Python and our open source libraries chartpy, findatapy and finmarketpy. We offer several services for clients which include:
- Alt Data Products / Creating exciting new datasets for clients to improve their own trading decisions and understand financial markets better
- Research Consulting / Writing bespoke quant research papers and developing bespoke models for clients
- Monetising Alt Data / Helping data companies and corporate institutions monetise their datasets through research and marketing services and aiding financial institutions to get into the alternative data age
- Software / Developing bespoke market analytics to be deployed on clients’ systems, building on our open source Python frameworks, including for backtesting, visualisation and TCA (transaction cost analysis)
- Teaching / We offer workshops for clients which include Python for finance and alternative data. We have taught at a number of large banks and funds.
Why the name Cuemacro?
Cue is defined as “a thing said or done that serves as a signal to an actor or other performer to enter or to begin their speech or performance.” In a trading context, market participants seek to understand the cues to enter into a trade. We seek to find these signals. Given our focus on macro markets, it was natural to put the two ideas to name our company Cuemacro.
Below we give examples of some of the client projects we have done at Cuemacro. Our clients have ranged from data vendors, to asset managers to quant hedge funds over the years, and have been based in both the US and also Europe. Our bespoke projects can range from delivering innovative new quant research for clients to developing analytics platforms for clients to run (such as TCA/transaction cost analysis).
- Bloomberg / We were commissioned by Bloomberg to write a research paper to show how their machine readable news could be used to trade FX. The project involved using a large dataset consisting of text, which we processed to construct sentiment scores and FX based trading signals. We also discussed how the dataset could be used to understand FX volatility around ECB and FOMC meetings. The paper was published on Bloomberg’s website and we also discussed the paper on Bloomberg TV.
- Investopedia / Investopedia commissioned us to conduct research to examine how web search data to their site could be used by investors. Their investor anxiety index is based on searches around subjects such as “short selling” which are consistent with investors concerns. We showed how the index could be used to trade equities. We talked about the project on Bloomberg TV.
- Freepoint Commodities / We were commissioned to examine how to apply a quant approach to commodities trading.
- A large European asset manager / We were commissioned by the firm to develop a Python based FX TCA library. Over nearly 2 years, we wrote the specifications with our client, and later implemented the framework, both a web based front end and also a back end for computation. Through the course of the project, we solved some crucial issues associated with the computation of large datasets. In particular, we worked on functionality to allow the computation to be distributed efficiently, to ensure the library was fast and could scale to the hardware. Elements of the project grew into our tcapy software product. Enterprise licences are available to purchase for tcapy.
- A Chicago proprietary trading firm / We were commissioned to develop an intraday FX trading strategy for the firm, which was later run profitably with real capital.
NLP & The Financial Sector NLP & The Financial Sector NLP & The Financial Sector NLP & The Financial Sector