Machine Learning: Sentiment Analysis in Investment Management

Date22 Nov 2021
Temps13:00 - 17:00
LieuZurich & online (subject to change)
Prof. Norman Schürhoff, SFI Senior Chair, Université de Lausanne
,
Dr. Matthias Uhl, Head of Analytics & Quantitative Modelling (AQM) in Investment Solutions, UBS Asset Management

Register now for this SFI Master Class and participate either in person at the Renaissance Tower Hotel in Zurich or online.
 
Depending on the development of the pandemic situation, this Master Class can be changed into an online-only activity.

 

Little more is known about the inventor of letterpress printing than that his name was Bi Sheng. The Chinese national invented mechanical book printing around the year 1041. Centuries later, Johannes Gutenberg brought European culture into the modern era with the same idea. Today, another revolution is taking place. Text becomes data. Text is being captured, processed, and analyzed by computers in order to understand and interpret language, on a massive scale.

 

Current Situation

In the financial world, the past decade has witnessed an explosion in the amount of data produced by companies—in the form of press releases and SEC filings, media outlets such as the Wall Street Journal, Financial Times, and New York Times, and web presences such as Twitter, Facebook, Google, and Wikipedia—but also the mass digitization of historical archives and administrative records. This new and widespread availability of text-based data coincides with major advances in the fields of machine learning/artificial intelligence (ML/AI), natural language generation (NLG), natural language understanding (NLU), and natural language processing (NLP).

The analysis of sentiment in natural language in combination with text-based computer analysis holds the promise of addressing a range of pressing problems faced by the banking and financial sectors. Investment managers can use sentiment analytics to “look through” noise in financial markets. In particular, it makes sense to identify longer-term cycles in news sentiment data and to formulate a model that identifies longer-term trends in the data in order to address the market-timing challenges faced by asset managers.
 

Objective

This course will provide participants with an overview of sentiment analysis and natural language. It will explore the economics of sentiment and highlight its applications in investment management. Best practices and trends will also be discussed via an interactive format.

Specific objectives are:
•    An understanding of big data & AI trends
•    An introduction to sentiment analytics and natural language
     o    Sentiment definition and classification
     o    Natural language generation (NLG), natural language understanding (NLU), and natural language processing (NLP)
•    A breakout session with group work on natural language
•    Understanding the economics of sentiment analytics and natural language
•    The application of natural language in investment management
     o    Sentiment analytics in the investment process
     o    News sentiment cycles
     o    Case studies across various asset classes
•    A study of best practices, trends, and outlook

 

Target Audience

The course is designed to provide all interested parties valuable insights into the world of machine learning, and to offer some initial hands-on coding experience.

 

SAQ Recertification

This Master Class is an acknowledged SAQ recertification measure for the CWMA profile and comprises four learning hours.

Register here if you are attending your first SFI Master Class