Norman Guo

Saint Louis University · Saint Louis, MO 63108 · norman.guo@slu.edu

I am an Assistant Professor of Finance at Saint Louis University. My research broadly focuses on FinTech, Machine Learning, Investment, and Corporate Finance, with a particular interest in uncovering hidden patterns on mutual funds, hedge funds, and financial analysts using explainable machine learning models.

Research Interest

  • FinTech: AI, Machine Learning, Deep Learning
  • Investments: Hedge Funds, Mutual Funds, Portfolio Management
  • Corporate Finance: Financial Analysts

I also build what I study: my day-to-day empirical work is run by an AI Research Orchestra — 28 specialized agents that carry a paper from idea to journal submission, under my direction.

Download Norman's Curriculum Vitae

Research

Publication

Hedging Performance of Multiscale Hedge Ratios [Paper]
with Jahangir Sultan, Antonios Alexandridis, Mohammad Hasan, 2019, Journal of Futures Markets

In this study, we combine the wavelet multiscale model and neural network to improve the hedging performance of multiple classes of assets over traditional hedging models.

Decoding Mutual Fund Performance: Dynamic Return Patterns via Deep Learning [Paper]
2026, Journal of Financial Stability

This paper uses a sequential deep learning model to uncover and predict dynamic patterns in mutual fund returns. A long-short portfolio based on the model generates a 2.8% annualized four-factor alpha that persists for up to four years.

Working Paper

Can Machines Understand Analyst Skills? [Paper]
with Sean Cao, Houping Xiao, Baozhong Yang

• Revise & Resubmit, Journal of Finance

We use machine learning to identify skilled financial analysts and aggregate their forecasts into a crowd wisdom-based earnings prediction. Machine-selected analysts persistently outperform expert-picked star analysts by leveraging nonlinear interactions of analyst characteristics rather than relation-based information.

Mapping the Midweek Mountain: The New Geography of Hybrid Work [Paper]
with Wei Jiang, Yaswanth Pothuru, Baozhong Yang

• Minor revision, Humanities and Social Sciences Communications

Using 41 billion mobile geolocation records, we document a lasting post-pandemic shift in work patterns: a 'midweek mountain' of office attendance on Tuesdays through Thursdays, with workers spending significantly more time at non-work locations during the workday.

The Impact of AI Adoption on Hedge Fund Performance [Paper]
with Zhen Shi, Baozhong Yang

• Under submission

We examine how AI adoption affects hedge fund performance and find that it improves returns by 2.64% annually, reduces risk, and leads to more diversified portfolios with less concentration in local stocks.

Machines in the Marketplace of Ideas: Automation and Rent Concentration in Prediction Markets
with Zhen Shi

Using Polymarket's full trade record of 532 million trades over 40 months, we show that machine-paced trading concentrates where prices can be transported from external betting lines, that its efficiency is real but borrowed, and that its profits concentrate in a handful of operators while the non-machine side pays a zero-sum $137.5 million.

Who Gains the Most from AI Accessibility? Evidence from Retail and Institutional Trades
with Sean Cao, Gregory W. Eaton, Pulak Ghosh, Jie He, Xiao Ren

We ask whether the arrival of generative AI narrows or widens the informational gap between retail and institutional investors, comparing trading behavior on both sides of the market around the diffusion of AI tools.

The Vulnerability Trap: How Sudden Stops Erode Firm Financial Health Through Supply Chain Destruction
with Anqi Jiao

• Under submission

We show that sudden stops in international capital flows destroy firms' supply chain networks, creating a vulnerability trap: financially fragile firms suffer the most network damage, which further weakens their financial health and amplifies exposure to future crises.

Why do actively managed mutual funds hold ETFs? Evidence on liquidity management

This paper examines why actively managed mutual funds hold ETFs and finds they serve as a liquidity management tool. Funds using index ETFs maintain performance regardless of investor flow, while non-users suffer lower returns during redemptions.

Selected Work in Progress

The Ripple Effect of Homelessness on Small Businesses and Lending
with Hadiye Aslan and Umut Yildiz
Career Concerns in Team-Managed Mutual Funds
with Vikas Agarwal, Honglin Ren, and Meng Wang
Modeling Investors' Voting Behavior Using Graph Neural Networks
with Sijin Wang

AI Research Orchestra

28 AI agents · 9 conductors · one principal investigator: you

Modern AI can draft, code, and analyze — but left alone in a chat window it forgets your research design, drifts off your question, and agrees with everything you say. The Orchestra is the opposite: a coordinated ensemble of specialized AI agents that runs my entire empirical pipeline — literature, data, regressions, drafts, referee responses — under locked research designs, adversarial review, and mandatory stops where the researcher decides. It has run my working papers for the past year, and its core is open source: install it as-is, or use it as the blueprint for conducting an orchestra of your own, in your own field.

  • It never loses the thread. Locked charters, decision logs, and belief ledgers carry months of context across every session, crash, and model swap.
  • Referee 2, pre-installed. Every design meets a hostile referee before data is pulled, and every draft survives an adversarial review loop before it ever reaches you.
  • It learns your field. Each project distills its hard-won lessons into permanent guard skills — my copy has taught itself 22 and counting.
  • You stay the PI. Agents draft, run, and check; nothing locks, ships, or reaches a co-author without your approval.

Explore the Orchestra Install from GitHub

Teaching

Introduction to Blockchain and Cryptocurrency

Saint Louis University
2022 - Present

Blockchain Technology, Cryptocurrency, & Business Disruption

Saint Louis University
2022 - 2023

Finance for Managers

Saint Louis University
2023 - 2024

Principles of Finance

Saint Louis University
2022 - Present

Blockchain and business disruption

Georgia State University

This course provides an introduction to blockchain technology and its disruptive roles in business. Students will have hands-on and problem solving experiences that can be useful in blockchain applications and innovation.

  • Fundamentals of Blockchain Technology
  • Blockchain and Business Disruption
  • Cryptocurrencies
  • Ethereum and Programming
  • Blockchain Platforms
2021 - 2022

Corporate Finance

Georgia State University
2019 - 2022

CFA Exam

Curriculum Lead and Lecturer, Utoollearning

Design and teach the course of Quantitative Methods, Portfolio Management, and Equity Investments in the CFA Level I exam.

2015 - 2016

Blockchain Business Cases

From classroom to capstone — student-built blockchain ventures.

In my Blockchain & Cryptocurrency course, students complete a capstone that takes a real business problem from boardroom to blockchain. Each team scopes a venture, drafts a full business plan, and ships a working Solidity smart-contract prototype on Ethereum. The result: technology fused with strategy — a showcase of how distributed ledgers can reshape industries from sports and entertainment to credit, intellectual property, and corporate governance.

Business Problem

Identify a pain point that incentives, trust, or transparency in a centralized system fail to solve.

Business Plan

Map the value proposition, stakeholders, token economics, and go-to-market strategy.

Solidity Execution

Deploy a working smart-contract prototype on Ethereum that proves the concept end-to-end.

Spring 2026 7 ventures · 3 winners

A blockchain-based fan loyalty platform that issues programmable NFT passes, letting artists and venues reward attendance, gate exclusive content, and combat ticket scalping with verifiable on-chain history.

Final Report Presentation

A decentralized registry that timestamps and signs contributions across creative teams, so writers, designers, and engineers can prove authorship, split royalties automatically, and resolve IP disputes without a middleman.

Final Report Presentation

A zero-knowledge framework that lets whistleblowers submit verified evidence of corporate or public-sector misconduct anonymously, with smart-contract-escrowed bounties released once authorities confirm the report.

Final Report Presentation

An on-chain certificate-of-authenticity protocol that pairs each physical product with an immutable digital twin, enabling buyers to verify origin, ownership history, and condition before purchase.

Final Report Presentation

A decentralized credit-scoring layer that aggregates on- and off-chain financial signals into a self-sovereign credit identity, giving thin-file borrowers a fair shot at lending markets worldwide.

Final Report

A consent-based data marketplace where individuals encrypt and license their personal data to researchers and advertisers, with smart contracts enforcing usage limits and streaming payments back to the data owner.

Final Report Presentation

A decentralized credentialing network that lets employers, universities, and certifying bodies issue tamper-evident proofs of skills, employment, and education that candidates can selectively share with recruiters.

Final Report Presentation
Spring 2025 6 ventures · 1 winner

AutoLedger replaces fragmented vehicle-history reports with a single immutable record: every sale, service, accident, and odometer reading is signed by the responsible party and written to Ethereum, so used-car buyers and lenders can finally trust what they see.

Final Report Presentation

BagBlock turns airline baggage tags into smart contracts: passengers stake a small premium, airline scans feed real-time custody data on-chain, and if a bag goes missing the policy auto-pays the traveler without a single claim form.

Final Report Presentation

The 2025 prototype of FanPass — a portable fan-loyalty NFT that survives across teams, seasons, and resale markets, giving sports franchises a richer view of their most engaged supporters and giving fans real ownership of their fandom.

Final Report Presentation

A token-curated crowdfunding platform built for university entrepreneurs: backers stake capital in milestone-gated smart contracts, founders unlock funds only as deliverables ship, and reputation accrues on-chain across multiple raises.

Final Report Presentation

IdeaFirst lets innovators register a hash of an early-stage idea on Ethereum to establish priority, then progressively reveal details to vetted collaborators or investors — a Web3 answer to provisional patents for the open-innovation era.

Final Report Presentation

SplitChain is a Web3 take on Splitwise: friends, roommates, and travel groups log shared expenses to a smart contract that nets balances and settles in stablecoins, eliminating the awkward 'who owes whom' spreadsheet.

Final Report Presentation

Foundational Blockchain Demos

Introduction of Blockchain and Cryptocurrencies