Wang Jiachen
Financial Technology & Quantitative Research
Summary
Master's student in Quantitative Investment & Asset Management at Central University of Finance and Economics. Previously earned a Bachelor's degree in Financial Technology from Southwestern University of Finance and Economics. Experienced in alpha factor mining, index enhancement strategies, ETF rotation, and applying deep learning to financial prediction.
Education
Master's — Quantitative Investment & Asset Management
Central University of Finance and Economics
Bachelor's — Financial Technology
Southwestern University of Finance and Economics
Experience
CTA Quantitative Research Intern
Beacon Investment Management
Mined 50+ low-correlation alpha signals from futures L1/L2 high-frequency data. Designed and implemented an LLM Agent-driven signal development automation system using Claude Code, with a layered architecture spanning Agent, Skills, Command, and Database layers.
Strategy Research Intern — Index Enhancement
Shanghai BlackWing Asset Management
Built full-stack index enhancement pipeline: multi-source alpha factor engineering, XGBoost with linear leaf nodes, incremental learning, adaptive large/small-cap model fusion, and ST risk prediction.
Research Intern — CTA Group
Chongwen Quantitative (Beijing)
Designed futures trend-following CTA strategy with trailing stop and portfolio management. Annualized return 15.9%, max drawdown 10.9%, Sharpe 1.07. Developed automated daily data update module.
Kaggle Competition R&D
Fanorm Technology
Developed solutions for JPX (top 10%, Sharpe 0.119) and Optiver (silver level, RMSPE 0.21524) competitions using LightGBM, gradient boosting ensembles, and TabNet.
Competitions & Awards
Sichuan Province FinTech Modeling Competition — First Prize (3rd & 4th Edition)
2022.10 – 2023.113rd edition: Predicted early loan repayment using Blending ensemble (top 3%). 4th edition: Built end-to-end data science workflow for customer repurchase prediction (top 3%).
Selected Projects
LLM-Driven Factor Mining & ETF Rotation Strategy
2025.10 – 2026.01End-to-end quant platform: LLM Agent factor discovery (GLM-4.5), multi-tier signal evaluation, rolling XGBoost/linear combination, and live ETF rotation trading.
Autoencoder-Driven Latent Factor Models for A-Share Market
2024.12 – 2025.04Thesis: Built PCA, IPCA, and conditional autoencoder latent factor models on 1996–2023 A-share data with 91 firm characteristics.
Candlestick Chart CNN Prediction for A-Share Market
2023.12 – 2024.07Attention-CNN on A-share candlestick images for binary prediction; long-short Sharpe ratio of 3.30 (weekly) and 1.50 (monthly).
Index Enhancement Strategy with XGBoost
2023.11 – 2025.01Full-stack index enhancement: factor engineering, XGBoost with linear leaf nodes, and adaptive market-style model fusion.
Green Finance DID Study on Labor Market Impact
2023.06 – 2023.12National-level innovation project: DID evaluation of green finance pilot zone policies using 2010–2021 A-share data.
Skills
Programming
Python, C, SQL, TypeScript
Data Science
pandas, Polars, NumPy, scikit-learn, XGBoost, LightGBM, PyTorch, Numba
Quantitative Finance
Alpha Factor Research, Backtesting, Portfolio Construction, Risk Analysis, Index Enhancement, ETF Rotation
Tools
Linux, Git, LaTeX, Docker, Jupyter, QMT, CUDA
Frontend
React, Next.js, Tailwind CSS