Anti-Gambling Trader is an open-source tool that uses statistical analysis (expectancy, significance tests, out-of-sample validation) to determine whether trading profits represent a repeatable edge or luck, and includes anti-scam features like language scanning and fake-performance forensics.

Stars

114

7-day growth

No data

Forks

14

Open issues

0

License

MIT

Last updated

2026-07-22

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It empowers users to objectively evaluate trading performance and detect investment fraud using rigorous math, operates entirely offline, and actively discourages gambling-like behavior rather than promising returns.

Who it is for

  • Individual traders in Taiwan stocks, US stocks, crypto, and forex
  • Investors suspicious of group-chat scams or guru claims
  • Quantitative developers looking to generate automated trading strategy skeletons
  • Anti-fraud researchers needing a forensic toolkit for performance claims

Use cases

  • Analyzing personal trade CSV/JSON/Excel files to get unbiased performance verdict
  • Scanning LINE or text conversations for scam language and risk levels
  • Validating a claimed win rate or monthly return against pure luck
  • Generating a scaffolded automated trading project with paper trading and safety gates

Strengths

  • Uses Python standard library only (zero external dependencies for core)
  • All trade data stays local; no server upload
  • Comprehensive anti-scam pipeline: scam-text scan, guru-check, survivorship bias simulator, forensics
  • Can produce backtestable strategy skeletons and live-trading project templates with multi-layer safety

Considerations

  • Requires basic command-line and Python familiarity (though a beginner guide is provided)
  • Statistical outputs are for educational use and do not constitute investment advice
  • Screenshot OCR may misread numbers and requires manual verification

README quick start

反詐投資王(Anti-Gambling Trader)

你在懷疑「投資群組是不是詐騙」「老師帶單可不可信」「我的交易到底是實力還是運氣」嗎? 這是一個免費開源的交易統計、投資反詐與自動化交易開發工具:把交易紀錄 (台股/美股/加密貨幣)丟進來, 它用期望值、顯著性檢定與樣本外驗證,給你統計證據判斷獲利更像可重複的優勢, 還是運氣+倖存者偏差(賭博);並內建詐騙話術掃描、假績效鑑識與假老師檢驗。 它也能把交易邏輯轉成可回測策略,並產生可接券商 API 的自動化交易程式專案。 交易分析資料全程在你自己的電腦上處理,不上傳任何伺服器。

一個誠實到不討喜的工具。它不會告訴你「你會賺錢」—— 不適合長期投資的,它會直接勸退你。 👉 急著找答案?先看 常見問題 FAQ:投資群組是詐騙嗎、 勝率 90% 可信嗎、出金要先繳稅正常嗎、被騙了怎麼辦。

🤖 不只分析,也能建立自動化交易程式。 scaffold 會產生自包含的策略、 風控、券商介面、資料源與圖表專案,提供 PaperBroker 與 13 種真實券商/交易所範本。 紙上模擬可直接執行;自行實作真實自動交易時,必須接妥券商 API、即時行情 runner, 並沿用四層安全檢查。預設生成的歷史 runner 不會送出真單;只有使用者自行填入金鑰、 完成 live runner 並明確解鎖後,live adapter 才可能送單。

English TL;DR — An honest, open-source (MIT) trading-performance analyzer for Taiwan securities and derivatives, US stocks, crypto and forex. It uses expectancy, significance tests (t-test + centered bootstrap) and out-of-sample validation to tell whether your P&L is a repeatable edge or survivorship-biased luck — and it will actively discourage you if it's the latter. Includes scam-language scanning, fake-performance forensics and a guru-claim probability checker. The statistical core uses the Python standard library, and trade-record analysis stays local. It can also generate backtestable strategy skeletons and automated-trading projects with paper trading by default and explicit safety gates for any user-built live connection.

👶 完全沒用過電腦命令?從這裡開始

如果你沒裝過 Python、沒用過終端機、也沒用過 AI,請看 新手快速上手指南 docs/quickstart.md —— 它從「怎麼裝 Python、怎麼打開終端機」開始,一步一步帶你上手。安裝後先打:

anti-gambling-trader start

畫面會依「完整紀錄、單筆交易、交易截圖,還是 LINE 對話」列出最短命令。 沒有試算表也能用 record 的五個短問題記一筆交易。

🛡 這個工具的反詐使命

台灣到處都是假飆股群、假二群、假 VIP 群、假名師、假績效截圖、保證獲利話術、 詐騙幣與假投資平台。它們絕大多數靠同一招:用倖存者偏差精選截圖, 讓你誤以為有穩賺的捷徑。

這個工具叫「反詐投資王」不是叫假的 —— 它存在的真正原因,就是用統計與數學 檢驗這些承諾。詐騙最怕的,就是你冷靜地把它的承諾丟進數學裡檢驗。

# 貼上群組對話,掃描詐騙話術(不給假百分比,只給風險等級)
anti-gambling-trader scan-text "老師帶單保證獲利,快加VIP客服"

# 檢驗老師的宣稱:「勝率90%、月報酬20%」純靠運氣出現的機率是多少?
anti-gambling-trader guru-check --win-rate 0.9 --trades 10 --monthly-return 0.2

# 用數學算出「連贏10次的神人」有多容易靠運氣出現
anti-gambling-trader survivorship

# 鑑識老師/平台宣稱的報酬序列是否有可疑徵兆(過度平滑、高得可疑的夏普)
anti-gambling-trader forensics --file 老師的月報酬.txt

# 互動式自我檢測
anti-gambling-trader scam-check

詳見 完整功能與判讀指南反詐指南FAQ

🆘 懷疑自己正在被詐騙? 立刻停止匯款,撥

Description

用統計學判斷你的交易是優勢還是賭博 — 支援台股/美股/加密貨幣,自動計算勝率盈虧比期望值、做顯著性檢定與樣本外驗證,並能產生個人交易程式專案

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482