Stock Embeddings - Representation Learning for Financial Securities

Understanding non-linear relationships among financial instruments has various applications in investment processes ranging from risk management, portfolio construction and trading strategies. Here, we focus on interconnectedness among stocks based on their correlation matrix which we represent as a network with the nodes representing individual stocks and the weighted links between pairs of nodes representing the corresponding pair-wise correlation coefficients. The traditional network science techniques, which are extensively utilized in financial literature, require handcrafted features such as centrality measures to understand such correlation networks. However, manually enlisting all such handcrafted features may quickly turn out to be a daunting task. Instead, we propose a new approach for studying nuances and relationships within the correlation network in an algorithmic way using a graph machine learning algorithm called Node2Vec. In particular, the algorithm compresses the network into a lower dimensional continuous space, called an embedding, where pairs of nodes that are identified as similar by the algorithm are placed closer to each other. By using log returns of S&P 500 stock data, we show that our proposed algorithm can learn such an embedding from its correlation network. We define various domain specific quantitative (and objective) and qualitative metrics that are inspired by metrics used in the field of Natural Language Processing (NLP) to evaluate the embeddings in order to identify the optimal one. Further, we discuss various applications of the embeddings in investment management.

Key Takeaways:

1. Grasp the Node2Vec algorithm and its role in financial correlation networks.
2. Understand domain-specific quantitative and qualitative metrics for evaluating embeddings.
3. Discover potential applications of stock embeddings in investment management.

This is a hybrid event. To attend online, join us on Zoom here at 6pm:
https://numfocus-org.zoom.us/j/82526680045?pwd=NE5HRXBIdUNmK0ROWGZXWDFnTW5adz09

Sponsor: [Tegus.com](https://www.tegus.com) will provide the meeting site, as well as pizza and soft drinks for the onsite participants.

• Tegus Chicago Address: 200 N. LaSalle Street. Suite 1100. Chicago, IL 60601
• Tegus Overview: Tegus is the leading market intelligence platform for key decision makers. We power some of the world’s most well-respected institutional investors, corporations, and consultancies through the largest and most comprehensive database of primary and market information. Our products and services enable clients to discover unmatched insights and answers to the most challenging questions they face to help them make better informed decisions. We are an end-to-end investment intelligence and research platform that modernizes the research processes. With an ecosystem that combines at-cost, on-demand expert calls with a 55K+ transcript library; quantitative financial workflows that streamline research across company disclosures, management presentations, earnings calls and filings; and 4K+ fully-drivable financial models and company benchmarking data, including every KPI and comparison that matters, Tegus enables investors to move faster, gather deep research and surface high-quality insights to drive better decisions. The company serves customers worldwide, including investment analysts, portfolio managers and key decision makers across public and private businesses in markets of all sizes.
• Logistics: To access the Tegus building, we require first and last names of those who RSVP'd by June 28th. Attendees will then present their IDs when they arrive at the front desk (right when they enter the building). They will be sent up in the elevator to the 11th floor where we will be.