Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Dynamic Pricing in Securities Lending Market: Application in Revenue Optimization for an Agent Lender Portfolio

Jing Xu, Yung-Cheng Hsu, William Biscarri

TL;DR

It is shown that existing contextual bandit frameworks can be successfully utilized in the securities lending market and that the contextual bandit approach can consistently outperform typical approaches by at least 15% in terms of total revenue generated.

Abstract

Securities lending is an important part of the financial market structure, where agent lenders help long term institutional investors to lend out their securities to short sellers in exchange for a lending fee. Agent lenders within the market seek to optimize revenue by lending out securities at the highest rate possible. Typically, this rate is set by hard-coded business rules or standard supervised machine learning models. These approaches are often difficult to scale and are not adaptive to changing market conditions. Unlike a traditional stock exchange with a centralized limit order book, the securities lending market is organized similarly to an e-commerce marketplace, where agent lenders and borrowers can transact at any agreed price in a bilateral fashion. This similarity suggests that the use of typical methods for addressing dynamic pricing problems in e-commerce could be effective in the securities lending market. We show that existing contextual bandit frameworks can be successfully utilized in the securities lending market. Using offline evaluation on real historical data, we show that the contextual bandit approach can consistently outperform typical approaches by at least 15% in terms of total revenue generated.

Dynamic Pricing in Securities Lending Market: Application in Revenue Optimization for an Agent Lender Portfolio

TL;DR

It is shown that existing contextual bandit frameworks can be successfully utilized in the securities lending market and that the contextual bandit approach can consistently outperform typical approaches by at least 15% in terms of total revenue generated.

Abstract

Securities lending is an important part of the financial market structure, where agent lenders help long term institutional investors to lend out their securities to short sellers in exchange for a lending fee. Agent lenders within the market seek to optimize revenue by lending out securities at the highest rate possible. Typically, this rate is set by hard-coded business rules or standard supervised machine learning models. These approaches are often difficult to scale and are not adaptive to changing market conditions. Unlike a traditional stock exchange with a centralized limit order book, the securities lending market is organized similarly to an e-commerce marketplace, where agent lenders and borrowers can transact at any agreed price in a bilateral fashion. This similarity suggests that the use of typical methods for addressing dynamic pricing problems in e-commerce could be effective in the securities lending market. We show that existing contextual bandit frameworks can be successfully utilized in the securities lending market. Using offline evaluation on real historical data, we show that the contextual bandit approach can consistently outperform typical approaches by at least 15% in terms of total revenue generated.
Paper Structure (20 sections, 9 equations, 5 figures, 2 tables, 1 algorithm)

This paper contains 20 sections, 9 equations, 5 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Background
  3. Securities Lending and Agent Lenders
  4. Trading Infrastructure and Market Mechanism
  5. Properties of a Good Pricing Strategy
  6. Contextual Bandit Problem Formulation & Related Work
  7. Contextual Bandit Formulation for an Agent Lender
  8. Related Work
  9. Reward Function & Evaluation
  10. The Agent Lender's Reward Function
  11. Offline Evaluation
  12. Experiment
  13. Experiment Setup
  14. Data
  15. Contextual Feature Construction
  16. ...and 5 more sections

Figures (5)

  • Figure 1: Interactions between entities in the securities lending process. Source: J.P. Morgan Asset Management
  • Figure 2: Borrowers sending multiple requests to a single lender for the same security with different expiration schedule
  • Figure 3: Booking preference as a function of bid for various $a_t^s$.
  • Figure 4: Comparison of average Booking Preference of 4 actions given the context (x axis - market share (top), other source of supply (bottom), y axis - Booking Preference).
  • Figure 5: Cardinal ranking of aggressiveness of 4 type of pricing strategies that in the action space.