Abstract: On a daily basis, the Research, Selection & Communication team at Van Lanschot Kempen monitor the vast and ever-changing seas of financial news, concentrating its immense volume of information into a handful of well-researched articles written for the benefit of the bank’s investment clients. These clients receive such articles at the discretion of their advisor who – in an ideal world at least – is very familiar with their clients’ investment interests (e.g. tech stocks, companies with high ESG ratings, emerging markets, …), and therefore perfectly placed to recommend relevant news to them. However, with a growing number of clients to support, it becomes impossible for advisors to recall the preferences of each and every client. How then, can we ensure that Van Lanschot Kempen’s news content reaches those clients who’ll be most interested?
Answering this question centres on solving two problems; firstly, how do we ascertain the investment interests of clients? and secondly, how do we summarize the content of a news article? For the latter we can simply apply NLP methods on the text body of each article. In solving the former, we apply those same methods to our rich dataset of historic interactions between advisor and client (whether these be emails, phone conversations, or face-to-face meetings). In both cases we leverage a cutting edge BERT pre-trained model to identify named entities (e.g. company names, locations, …) within text. This allows us to represent each article and client as a vector within the same N-dimensional space (where N is the number of named entities in our dataset), and thus calculate a similarity metric between articles and clients. This similarity score goes on to drive our recommender engine to suggest an advisor’s most relevant clients for a given article.
The key breakthroughs from this project which I’ll cover in this talk are:
- Leveraging in-house email and meeting note data to build a client profile
- Applying cutting-edge BERT pre-trained model to identify named entities relevant to the financial sector
- Productionalizing a recommender system to aide and guide traditional financial advisors
Bio: Alun is a Senior Data Scientist at Van Lanschot Kempen, an independent wealth manager in the Netherlands which has been helping clients reach their financial goals for almost 300 years. As a data scientist his interests are; the application of AI in Finance, Recommender Systems, and NLP. As a human his interests are; music, poetry and dogs of all shapes and sizes.
Alun Biffin, PhD
Senior Data Scientist | Van Lanschot Kempen