Modeling Post-Earnings Drift with Genetic Algorithm-Tuned XGBoost
Summary
The paper applies supervised machine learning to post-earnings-announcement drift (PEAD), an equity anomaly in which returns continue to move after earnings news. Its model uses XGBoost and engineered fundamental and technical features built from quarterly announcement data for 1,106 Russell 1000 companies from 1997 through 2018. A genetic algorithm is used to optimize the model. The analysis examines drift direction and how its drivers vary across industry sectors and calendar quarters.
The authors report that the model produces credible forecasts of drift direction and can sort out-of-sample stocks into long and short groups with more favorable returns, which they suggest may support market-neutral strategy development. They also address implementation difficulty: prices can move while an event-driven trade is being entered, and the paper presents a tactic intended to reduce that problem. The description does not provide performance figures, transaction-cost estimates, or detailed validation procedures, so the reported results do not establish net profitability or persistence.
Key ideas
- The study uses XGBoost to forecast the direction of post-earnings-announcement drift.
- Its engineered features combine fundamental and technical information around quarterly announcements.
- A genetic algorithm optimizes the model, and the analysis covers 1,106 Russell 1000 firms from 1997 to 2018.
- The reported drivers of drift vary by industry sector and quarter.
- Out-of-sample stock sorting and an entry tactic address portfolio formation and moving prices, though profitability details are not supplied.
Tags
Full text
# Capturing dynamics of post-earnings-announcement drift using genetic algorithm-optimised supervised learning # Capturing dynamics of post-earnings-announcement drift using genetic algorithm-optimised supervised learning While Post-Earnings-Announcement Drift (PEAD) is one of the most studied stock market anomalies, the current literature is often limited in explaining this phenomenon by a small number of factors using simpler regression methods. In this paper, we use a machine learning based approach instead, and aim to capture the PEAD dynamics using data from a large group of stocks and a wide range of both fundamental and technical factors. Our model is built around the Extreme Gradient Boosting (XGBoost) and uses a long list of engineered input features based on quarterly financial announcement data from 1,106 companies in the Russell 1000 index between 1997 and 2018. We perform numerous experiments on PEAD predictions and analysis and have the following contributions to the literature. First, we show how Post-Earnings-Announcement Drift can be analysed using machine learning methods and demonstrate such methods' prowess in producing credible forecasting on the drift direction. It is the first time PEAD dynamics are studied using XGBoost. We show that the drift direction is in fact driven by different factors for stocks from different industrial sectors and in different quarters and XGBoost is effective in understanding the changing drivers. Second, we show that an XGBoost well optimised by a Genetic Algorithm can help allocate out-of-sample stocks to form portfolios with higher positive returns to long and portfolios with lower negative returns to short, a finding that could be adopted in the process of developing market neutral strategies. Third, we show how theoretical event-driven stock strategies have to grapple with ever changing market prices in reality, reducing their effectiveness. We present a tactic to remedy the difficulty of buying into a moving market when dealing with PEAD signals.
Shown in full with attribution under the source's licence. Licence: abstract CC0
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.