High Frequency Trading in MMORPG Markets using Luigi, Pandas, and Scikit learn
summary
A Python pipeline harvests EVE Online market data via the game API for about 2,500 item types making ~5,000 calls, Luigi parallelized 20 workers to fetch and retry robustly, pandas aggregates per‑item features like margin and daily volume, and scikit-learn for supervised labels trains on a weeklong experiment. The goal is >1 billion ISK per month and a test run grows net worth from ~2B to ~4B ISK in a month, so the system works.
AI-written summary · about
chapters (7)
- 0:00High frequency trading in games
- 1:48Trading pipeline overview
- 8:10Luigi for API data
- 16:38Pandas data transforms
- 20:59Scikit-learn trade selection
- 23:48Pipeline beyond games
- 24:54Q&A on automation
related talks
42mMarket Analytics in EVE with Ruby
39mData Pipelining for Real-time ML Models
38mPySpark and Warcraft Data
32mLarge-scale machine learning pipelines using Luigi,...n
23mCustom-made games with machine learning and big data
01h 26mImplementing a highly scalable Stock prediction system with R, GemFire and Spring XD
30mHow to build a stock market money printing machine with AI
33mReal-time Trade Data Processing and Machine Learning at Giga-Sca...