Jien Weng

I am an AI researcher with Monash University Malaysia and a proprietary research team. Most of the work is mathematical modelling, multi-agent reinforcement learning, and market microstructure. I also consult, currently with Quandatics on data and AI work in finance. If that is what brought you here, see Work With Me.

Recent Notes

index

What I mostly care about is the information side of learning problems. What does the agent get to observe, and what does the model assume about the world it is in? In my experience that decides more than the choice of algorithm does. The same question keeps turning up everywhere I work: in cooperation problems in reinforcement learning, in trade execution, lately in environmental systems too.

Current Work

  • Information design and credit assignment in multi-agent cooperation
  • Optimal execution with predictive alpha signals

Selected Publications

The Primacy of Information Design Over Algorithm Selection in Multi-Agent Cooperation
Jien Weng Lai, Wei Lun Tan, Ying Loong Lee, Ming Fai Chow · Under Review @ IEEE Social Computation
Apr 2026
Abstract

A full-factorial experiment in the Public Goods Game shows that information regime and incentive strength explain 85.8% of cooperation-rate variance; algorithm choice accounts for just 3.8%. Agents with the least information cooperate most (83% vs 42% under full observation), attributable to state-space compression. TreeSHAP and Shapley-variance decomposition confirm information structure, not algorithm selection is the primary design lever for cooperation.

  • Multi-Agent Reinforcement Learning
  • Public Goods Game
  • Information Design
  • Cooperation
Jien Weng Lai · SSRN · Published
Apr 2026
Abstract

The execution of large portfolio transactions requires balancing market impact and adverse price drift. The Almgren-Chriss (2001) framework provides a meanvariance trade-off for martingale price processes, but practitioners often utilize short-term alpha signals. This paper re-evaluates the optimal liquidation problem using Stochastic Optimal Control. By incorporating a mean-reverting alpha signal into the price dynamics, we derive a closed-form solution using the Hamilton-Jacobi-Bellman (HJB) equation. The resulting optimal trading rate is an affine function of the current inventory and the predictive signal. This results in a trajectory that adjusts execution speed to capture transient alpha. This work provides a transparent and additive framework for institutional execution desks.

  • Optimal Execution
  • Alpha Signals
  • HJB Equation
  • Stochastic Control
  • LQG Regulation
  • Quantitative Finance
Cite
@misc{lai2026execution,
  title        = {Optimal Execution with Alpha Signals},
  author       = {Lai, Jien Weng},
  year         = {2026},
  howpublished = {SSRN Working Paper},
  doi          = {10.2139/ssrn.6323159},
  url          = {https://ssrn.com/abstract=6323159}
}

If any of this overlaps with a problem you are working on, email me. The consulting side is described in Work With Me.