Interested in MFE? Visit our Master of Sci. in Financial Engineering.
"A stable, efficient, and consistent modern society must be founded upon a solid financial system. From a student loan hatching a warm sunrise to a retirement fund securing a peaceful sunset, the so-called Main Street and Wall Street are actually bound together as the flesh and the bone do, mutually supporting and shaping each other.
Financial engineers therefore must recognize the profound social responsibilities on our shoulders, and become the forefront lines of defense of a stable, efficient, and consistent financial system. As a result, from data collection, model building and testing, system implementation, to the delivery of client services, we should emphasize the notion of risk-adjusted returns and passionately build a culture by which risk and returns are as inextricable as the universal entanglement of Yin-Yang."
Jackie Shen (2013)
==================================================================================================================================
Starting in 2025, we will also cover Generative AI and Agentic AI, esp. their broad applications and risk management in Finance.
Jackie Shen (May 24, 2026), Black-Box AI Agents (B2A2) inside Pandora's Box, available at SSRN #6822458; Youtube companion video.
[Abstract] Once the box is opened, B2A2's will baffle most existing control frameworks within modern corporate environments, and potentially spark another pandemic. They must be designed with a minimum set of requirements on transparency and control. The discussion herein mostly focuses on investment banks, but the principles or frameworks are universal.
[Keywords] Agents, Agentic Teams, Full Autonomy, Black Box, Transparency, Memory Cost, Backdoor Internet Search, Internal Data, On-the-Fly Coding, Compliance AI Agents (CAA).
Jackie Shen (Sept 6, 2025), GenAI on Wall Street -- Opportunities and Risk Controls, available at SSRN #5451015 or arXiv.2509.05841.
[Abstract] We give an overview on the emerging applications of GenAI in the financial industry, especially within investment banks. Inherent to these exciting opportunities is a new realm of risks that must be managed properly. By heeding both the Yin and Yang sides of GenAI, we can accelerate its organic growth while safeguarding the entire financial industry during this nascent era of AI.
[Keywords] Generative AI (GenAI), Large Language Models (LLM), Agents, Structured, Unstructured, JSON, Coding-Free, Agentic Network, Data Privacy, Information Barriers, Hallucination, Brainwash, Gossips, Generalization
[Youtube] Some anonymous colleague also kindly created this Youtube video via NotebookLM, which offers a friendly approximation to the main text.
Jackie Shen (March, 2024), White Paper - DQT Transaction Cost Models (TCM) (online), a white paper for the proprietary TCM model of production quality, by the Deep QuanTech, March, 2024. Please try it out via the free Web GUI.
[Summary] Transaction Cost Models (TCM) (or also called Liquidity Cost Models (LCM)) are fundamental for forecasting pre-trade shortfalls, computing or assessing broker-dealer commissions or markups, and developing the new generation of portfolio optimizers that incorporate liquidity qualities and liquidation costs, etc. A TCM model projects the expected liquidation costs out of the jungle of multiple uncertain stochastic factors of Brownian prices, market volumes, security volatilities, bid/ask spreads, and so on.
From top investment banks to major execution agency houses, traditional TCMs can only be calibrated from the massive individual trading data privately owned by these entities. But the big data cannot overcome the curse of the extremely low signal-to-noise ratios (SNR). In this work, for the first time in the financial world, we are able to deliver a TCM model of production quality, based entirely on all available sources of public data. Please try it out via our free Web GUI.
[Novelty] A TCM model based solely on public data has never been thought possible in finance, before us.
Jackie Shen (Feb, 2024), White Paper - DQT Crypto Factor Models (online), a white paper for the first publicly released crypto factor model of production quality, by the Deep QuanTech, February, 2024.
[Summary] From Nobel Laureates to Wall St, the notion of systematic factors is critical for deciphering and disentangling the stochastic complexity behind economies or the financial world. It allows to make strategic and systematic investment decisions, as well as to effectuate stylized risk controls. In this work, with the seamless integration of Quant skills and Tech toolkits, we deliver the first stochastic factor model of production quality for the ever evolving universe of cryptos.
[Novelty] The novel metric of entropy of the entire universe introduced here is profound, in our opinion.
Jackie Shen, Nine Challenges in Modern Algorithmic Trading and Controls, Algorithmic Trading and Controls, 1(1):1-9, 2021. Also at SSRN #3767062 or ArXiv.2101.08813.
[Keywords] Algos, liquidity, portfolio, correlation, special days, derivative pricing, universe, clustering, machine learning, auctions, shortfall, transaction cost, unit test, regression test, simulation, automated controls.
[Remark] We discuss nine major challenges that contemporary algorithmic trading faces. Some of them are at the strategy level while others are more concerned with the automated controls and risk management of algorithmic trading. Revenues and risks are the very Yin-Yang of algorithmic trading, and so are the smart quantitative strategies and automated risk controls. They are inseparable and should remain so.
J. Shen (April, 2020), A Stochastic LQR Model for Child Order Placement (COP) in Algorithmic Trading. SSRN #3574365.
[Keywords] Child order placement (COP), dynamic programming, LQR, delay cost, spread cost, impact cost, information leakage, Poisson hits, passive, aggressive, Bellman equation, optimal policy, positive definite matrix.
[Remark] It is impossible to encapsulate all realistic market complexities into a single clean and rigorous mathematical model for COP. In the spirit of reductionism, the current novel work presents a self-contained and rigorous dynamic programming COP model based on stochastic linear-quadratic regulators (LQR). It captures the intriguing interplay between aggressive sniping and passive sitting, and has a closed-form solution.
J. Shen (June, 2017), Hybrid IS-VWAP Dynamic Algorithmic Trading via LQR. SSRN #2984297.
[Keywords] Dynamic programming (DP), LQR, IS, VWAP, slippage, spread, delay cost, impact cost, Bellman equation, optimal policy, stability.
[Remark] We develop a solid DP trading model with closed-form solutions that are unconditionally stable, and more importantly, make actual economic sense. It is the first DP model implementing a quasi risk aversion mechanism that can only be achieved previously by static trading models.
J. Shen, A Pre-Trade Algorithmic Trading Model under Given Volume Measures and Generic Price Dynamics (GVM-GPD), Applied Math. Research eXpress, Oxford Univ. Press, 2015 (1): 64-98, 2015 (Also available at SSRN #2327835 (2013)).
[Keywords] Algorithmic trading, price dynamics, impact cost, quadratic programming, compact positive operator, Hilbert spaces.
[Remark] For the first time in the literature, we have solved the pre-trade problem comprehensively (i.e., honoring key clients constraints), completely (i.e., existence and uniqueness via infinite-dimensional Hilbert spaces), and practically (i.e., implementing via quadratic programming).
J. Shen and Y. Yu (October, 2014), Styled Dynamic Algorithmic Trading and the MV-MVP Style. SSRN #2507002.
[Keywords] Dynamic programming, style, moneyness, aggressive, passive, participation, parametric, stochastic, binomial trees.