Please rotate your device to landscape mode to view the charts.

Informed Trading Intensity

Journal: Journal of Finance

Date: 20240401

Author: Bogousslavsky, Vincent; Fos, Vyacheslav; Muravyev, Dmitriy

Abstract:
We train a machine learning method on a class of informed trades to develop a new measure of informed trading, informed trading intensity (ITI). ITI increases before earnings, mergers and acquisitions, and news announcements, and has implications for return reversal and asset pricing. ITI is effective because it captures nonlinearities and interactions between informed trading, volume, and volatility. This data-driven approach can shed light on the economics of informed trading, including impatient informed trading, commonality in informed trading, and models of informed trading. Overall, learning from informed trading data can generate an effective informed trading measure.

Link: Google Scholar

Key Findings

Detection of Informed Trading

The Informed Trading Intensity (ITI) measure effectively detects Schedule 13D trades with high accuracy, outperforming existing measures of informed trading

Predictive Power

ITI increases before major information events like earnings announcements, M&As, and news releases, demonstrating strong predictive capabilities

Return Prediction

Higher ITI is associated with higher future monthly returns, with a Fama-French four-factor alpha of 6.42% annualized for the top-minus-bottom decile portfolio

ITI Performance Across Trading Types

  • ITI(13D) achieves highest adjusted R² of 9.86% in detecting Schedule 13D trades
  • ITI(impatient) demonstrates stronger detection capability than ITI(patient)
  • Consistent performance across different types of informed trading

Portfolio Returns Based on ITI Measures

  • ITI(13D) generates highest monthly FF4 alpha of 0.52%
  • ITI(impatient) shows stronger return prediction than ITI(patient)
  • Consistent positive relationship between ITI and future returns

ITI Around Information Events

  • Significant increase in ITI before earnings announcements
  • Sustained elevation in ITI following news events
  • Pattern consistent across different types of information events

Contribution and Implications

  • Introduces a novel data-driven approach to measure informed trading using machine learning
  • Demonstrates the importance of distinguishing between patient and impatient informed trading
  • Provides evidence of commonality across different types of informed trading
  • Offers practical applications for detecting informed trading before major corporate events

Data Sources

  • Trading Performance Chart: Based on Table II and Table III showing adjusted R² values for different ITI measures
  • Portfolio Returns Chart: Constructed using data from Table XI showing Fama-French four-factor monthly alphas
  • Events Chart: Derived from Figure 4 showing ITI patterns around earnings announcements