Skip to content
View Rockefarmer's full-sized avatar
4 followers · 14 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report Rockefarmer

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Rockefarmer/README.md

Hi there, I'm Qiping "Rockefarmer" Wu

Former Fund Manager turned FinTech ML Engineer
Quantitative Research | Financial Forecasting | Time-Series Modeling | Financial NLP

I am building at the frontier of finance and machine learning—bringing together decades of institutional market experience and modern AI methods to design practical forecasting and research systems.

Core Expertise

  • Time-Series Forecasting: ARIMA, SARIMA, LSTM, TFT
  • Financial NLP: FinBERT, LLM-based earnings call analysis
  • Quantitative Modeling: equity research, revenue forecasting, volatility signals
  • Applied AI for Finance: turning market narratives and structured data into actionable models

Education

  • MSc in Electrical and Computer Engineering (Software Engineering, Thesis-Based) — Lakehead University
  • MBA in Finance — Fudan University
  • BEng — Tongji University

What I'm Working On

Academic Research

  • Thesis-based MSc research on AI/ML applications in financial forecasting
  • Temporal Fusion Transformer models for multi-horizon corporate revenue prediction
  • Hybrid forecasting systems that integrate structured financial data with textual signals

Technical Projects

  • Financial Forecasting Pipelines: ARIMA/SARIMA → LSTM → TFT
  • Financial NLP Systems: earnings call analysis using FinBERT and LLMs
  • S&P 500 Predictive Modeling: quarterly revenue and net-income forecasting
  • Volatility Research: VIX-related signal generation and risk management
  • Feature Engineering: scalable structured and text-derived financial features
  • Backtesting Frameworks: rigorous, leakage-free evaluation pipelines for quantitative strategies

Featured Interests

  • Multi-horizon time-series forecasting
  • Interpretable deep learning for finance
  • Multimodal modeling with market text and fundamentals
  • Institutional-grade quantitative research workflows
  • Practical AI tools for investment decision support

Connect With Me

Pinned Loading

  1. Securities-Investment-Architecture-and-Practice Securities-Investment-Architecture-and-Practice Public

    A practitioner-focused, serialized book on designing securities investment systems: data pipelines, risk controls, and system architecture. Includes Python code, diagrams, and reproducible examples.

    1

  2. Rockefarmer Rockefarmer Public

    1

  3. TFT_for_Forecasting_SP500_Quarterly_Revenue TFT_for_Forecasting_SP500_Quarterly_Revenue Public

    We evaluate the Temporal Fusion Transformer (TFT) for firm-level quarterly revenue on 155 continuously listed S&P 500 firms from 1995Q1–2025Q2

    Python 1

  4. tft-h4-revenue-forecasting tft-h4-revenue-forecasting Public

    Multi-horizon (h=1–4) quarterly revenue forecasting using Temporal Fusion Transformer (TFT) on structured financial data

    Python 1

  5. tft-hybrid-revenue-forecasting tft-hybrid-revenue-forecasting Public

    Hybrid multimodal revenue forecasting combining TFT with FinBERT sentiment and Llama-3 narrative features

    Python 1