algotrading / aitrading / quant / buildinpublic / tradingbot
20 things to do before you deploy an AI trading bot
Before deploying an AI trading bot, work through this 20-item research checklist from Austin Starks. It covers technical, fundamental, and economic indicators; alternative data; look-ahead and selection bias; overfitting; and walk-forward analysis.
The checklist also includes probability, uncorrelated markets and strategies, the ReAct paper, tool calling, MCP servers, backtesting, and paper trading. This short video names the topics to investigate before going live; it is a starting point for further study.
Transcript
0:00Download Codex
0:01read about technical indicators
0:03read about why technical indicators don't work
0:05read about fundamental indicators
0:07read about why fundamental indicators don't work
0:09read about economic indicators
0:11read about why no indicators work
0:13read about alternative data
0:15read about why collecting alternative data is hard
0:17read about look-ahead bias
0:19read about selection bias
0:20read about overfitting
0:22read about walk forward analysis
0:24read about uncorrelated markets
0:25read about probability
0:26read about uncorrelated strategies
0:29read the original ReAct paper
0:31read about tool calling and MCP servers
0:33read about backtesting
0:34and read about paper trading
Join the conversation
Loading conversation…