LEMs: A Primer On Large Execution Models
Remi Genet, Hugo Inzirillo
TL;DR
Large Execution Models (LEMs) address the problem of optimal execution under flexible time windows and mixed quantity/notional objectives by decoupling market information processing from allocation decisions. The approach uses a shared feature extraction pipeline built on Temporal Kolmogorov-Arnold Networks (TKANs), Variable Selection Networks (VSNs), and multi-head attention to produce a rich execution-context, which is then fed into independent Step-wise FusedMLP decision blocks for each execution scenario. Empirical evaluation on intraday cryptocurrency data and multi-day Dow Jones equities demonstrates that time-bound flexibility enables substantive benchmark beating (relative to VWAP/TWAP) while controlling risk, with a single model capable of handling multiple asset classes and execution modalities. The results underscore the practical potential of deep learning-based execution models for contracts such as share buybacks and other non-vanilla VWAP-like mandates, while signaling avenues for future enhancements in market microstructure modeling and multi-asset coordination.
Abstract
This paper introduces Large Execution Models (LEMs), a novel deep learning framework that extends transformer-based architectures to address complex execution problems with flexible time boundaries and multiple execution constraints. Building upon recent advances in neural VWAP execution strategies, LEMs generalize the approach from fixed-duration orders to scenarios where execution duration is bounded between minimum and maximum time horizons, similar to share buyback contract structures. The proposed architecture decouples market information processing from execution allocation decisions: a common feature extraction pipeline using Temporal Kolmogorov-Arnold Networks (TKANs), Variable Selection Networks (VSNs), and multi-head attention mechanisms processes market data to create informational context, while independent allocation networks handle the specific execution logic for different scenarios (fixed quantity vs. fixed notional, buy vs. sell orders). This architectural separation enables a unified model to handle diverse execution objectives while leveraging shared market understanding across scenarios. Through comprehensive empirical evaluation on intraday cryptocurrency markets and multi-day equity trading using DOW Jones constituents, we demonstrate that LEMs achieve superior execution performance compared to traditional benchmarks by dynamically optimizing execution paths within flexible time constraints. The unified model architecture enables deployment across different execution scenarios (buy/sell orders, varying duration boundaries, volume/notional targets) through a single framework, providing significant operational advantages over asset-specific approaches.