Skip to content
Nat Lee

Keyboard shortcuts

Turn these off if they get in the way of a screen reader or voice control. The setting is saved in this browser.

1
Home
2
Projects
3
About
4
Experience
/
Search projects
?
Show this panel

AI/ML

Power Trading AI System

International Power Trading Strategy Development

Spot-price forecasting and trading strategies for the Japanese and Australian power markets. The repository is private, so screenshots will have to do.

Role
Senior Engineer - Lead Developer
Period
2024.12 – Present
Status
Active
Theme
Energy & forecasting
Power Trading AI System, screenshot 1

Overview

Leading the development of sophisticated AI trading strategies for international power markets. The system uses advanced time series analysis and machine learning models to predict electricity spot market prices, helping traders make data-driven decisions in volatile energy markets.

The problem

  • Handling volatile electricity market data
  • Real-time prediction requirements
  • Integration with existing trading systems
  • Multi-market data synchronization

What I did

  • Implemented robust time series models with PyTorch
  • Built scalable data pipeline with Elasticsearch
  • Created modular API architecture with Django
  • Developed comprehensive testing framework

Results

  • Successfully deployed prediction models for Japan market
  • Achieved 85% accuracy in price trend prediction
  • Reduced trading decision time by 60%
  • Enabled expansion to Australia market

Features

  • Spot market price prediction models
  • Real-time data processing pipeline
  • Trading strategy optimization
  • Risk assessment algorithms
  • Performance monitoring dashboard
  • Power Trading AI System, screenshot 2
  • Power Trading AI System, screenshot 3
  • Power Trading AI System, screenshot 4
  • Power Trading AI System, screenshot 5
  • Energy & forecasting

    Solar Power Prediction System

    Time-series models that forecast solar output for an energy-storage demonstration site, scheduled with Airflow. The sun is punctual; the clouds are the problem. The repository is private, so the dashboards here are redrawn on simulated data.

    2023Completed