PPPT General quantitative, AI, research, engineering, PhD, and finance conversation / 15 min
Professional portrait of Pengyi Peng in a dark suit against a plain background

PPT15-001 / SELF INTRODUCTION / 15 MIN

I turn quantitative ideas into systems and evidence.

Pengyi Peng | Mathematics, AI, quantitative research, engineering, and financial markets.

Evidence: profile-positioning-001
01

01 / JOURNEY

My path converges on AI-native quantitative systems.

Mathematics -> markets -> software -> AI-native research and trading.

  • 2018-2024: Mathematics, applied mathematics, and complex systems
  • 2024: WorldQuant competition research and external ranking
  • 2025-now: banking, securities, open source, and independent systems
Evidence: education-kcl-001 / education-bsc-001 / experience-pingan-001 / experience-citic-001
02
Illustrative mathematical research room with equations, networks, and time-series diagrams

02 / QUANTITATIVE FOUNDATION

Mathematics taught me to model systems, not just fit models.

State, transition, and failure boundary come before optimization.

  • MSc Complex Systems Modelling, KCL Mathematics
  • BSc Mathematics and Applied Mathematics
  • Explicit assumptions, point-in-time information, and falsifiable tests
Evidence: education-kcl-001 / education-bsc-001 / education-bsc-achievement-001
03
Illustrative quantitative research workspace with charts, distributions, and market data

03 / FIRST QUANT EVIDENCE

Competition results opened the door; reproducibility sets the standard.

Historical rank demonstrates iteration, not portable alpha.

  • IQC 2024: global 232 / 34,142; top 0.7%; UK 5
  • MAPC 2024: global 11 / 850; UK 1
  • Next standard: independent data, costs, robustness, and stop rules
Evidence: competition-iqc-001 / competition-mapc-001
04

04 / RESEARCH GOVERNANCE

I now build research loops that can reject weak ideas.

Six candidates. Four data families. One quarantine. One negative control.

  • Sentiment, news, price-volume, and options/volatility coverage
  • alpha078 quarantined until publication timestamps make Delay 0 identifiable
  • alpha027 retained as a weak control so the pipeline must reject bad ideas
Evidence: project-pwol-batch001
05

05 / FAILURE AS OUTPUT

A failed strategy can still improve the system.

PTFT rejected fragile trend results; PMMT converted directional inventory into risk specification.

  • PTFT: the positive snapshot failed broader timeframes and annual windows
  • PMMT v0.2: -1,561.58 USDT and -16.22% MDD exposed structural inventory risk
  • PMMT v0.3 risk tests pass; economic improvement remains UNMEASURED
Evidence: project-ptft-benchmark001 / project-pmmt-v03
06
Illustrative modular AI agent laboratory with memory, tools, evaluation, and Human review stations

06 / AI-NATIVE RESEARCH

AI belongs inside the research infrastructure.

Delegate bounded work; preserve schemas, evidence, evaluation, and Human decisions.

  • Collect -> test -> compare -> review -> decide
  • Versioned workflows, deterministic states, audit traces, and regression tests
  • Multi-model collaboration is benchmarked on quality, cost, and reviewability
Evidence: project-agent-systems-001 / skills-engineering-001
07
Illustrative open-source engineering workspace with code review, dependency graphs, and test dashboards

07 / EXTERNAL REVIEW

Open source makes engineering judgment externally reviewable.

A useful change is bounded, testable, and improved by another person's challenge.

  • LightRAG: truncation and empty-response failure semantics
  • NautilusTrader: deterministic request tests without fixed waits
  • Tencent WeKnora: archived-page statistics boundary
  • Four verified upstream-merged fixes in the current evidence record
Evidence: opensource-lightrag-001 / opensource-nautilus-001 / opensource-weknora-001
08
Abstract price and volume wave used to represent the measured research-to-trading loop

08 / RESEARCH TO TRADING

I am building the full research-to-trading loop.

Data -> research -> state -> strategy -> risk -> execution -> feedback.

  • PWOL and PAAT: point-in-time research and rejection discipline
  • PTFT + PMMT + State Agent: trend, market making, and explicit routing
  • End-to-end SMT economics remain UNMEASURED until fixed replay
Evidence: project-pwol-batch001 / project-ptft-benchmark001 / project-pmmt-v03 / project-smt-three-axis-001
09
Illustrative Shenzhen financial workspace with capital-flow diagrams, reports, and city skyline

09 / REAL-MARKET CONTEXT

Banking keeps the market model connected to real capital.

Markets are also balance sheets, funding needs, client constraints, incentives, and operations.

  • Ping An Bank: corporate, retail, operations, settlement, cash management, and credit workflows
  • CITIC Securities: quantitative private-fund comparison and manager communication
  • Finance experience is context for research, not a substitute for technical evidence
Evidence: experience-pingan-001 / experience-citic-001
10
Illustrative future research laboratory connecting experiments, systems, and institutional collaboration

10 / OPERATING SYSTEM

My operating system turns learning into compounding infrastructure.

Learn -> build -> test -> ship -> document -> reuse.

  • AI: agents, memory, retrieval, tools, evaluation, and model collaboration
  • Quant: data, alpha, trend, market making, state, risk, and execution
  • Finance: banking, FICC, capital, clients, and real operating constraints
Evidence: profile-positioning-001 / project-agent-systems-001 / skills-engineering-001
11

11 / DIRECTION

Research. Build. Compound.

AI-native quantitative systems, grounded in evidence and connected to real markets.

  • github.com/pengpengyi92
  • pengyicv.pages.dev
  • Which part of the research loop would you challenge first?
Evidence: profile-positioning-001
12