Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

Shoebox: a bookkeeper for freelancers that never sees your bank statement

Описание и применение

Shoebox — инструмент для фрилансеров, который автоматически классифицирует банковские транзакции в категории Schedule C, обучается на ваших исправлениях и генерирует налоговые отчёты, работая полностью в браузере без передачи данных на сервер.

Задача

Freelancers spend a weekend manually categorizing bank statements, risking errors and relying on paid services that expose sensitive data.

Результат

Shoebox reduces manual clicks from 17 to zero after learning, processes 321 transactions in ~3.5 s, and eliminates the need for server‑side data handling.

Рабочий процесс

  • Upload CSV from any bank or card
  • Shoebox guesses column mapping and shows preview
  • User fixes mapping if needed
  • Shoebox sorts transactions into Schedule C categories using embedding model
  • Lines with confidence ≥0.5 are filed automatically
  • Uncertain lines appear in a grouped "Needs review" list
  • User answers merchant questions, creating rules
  • Shoebox updates future classifications
  • Shoebox aggregates totals, estimates taxes, and exports CSV/Markdown or prints

Доказательства

Shoebox guesses which column is which (one amount column or separate debit/credit, day-first dates, cards that list purchases as positive numbers) and shows a preview so you can fix it.

Источник

It sorts every transaction into US Schedule C categories: meals, travel, software, contract labor, personal, transfers and so on.

Источник

The AI runs inside your browser tab. There's no server, no account, no bank login and no analytics.

Источник

After the first visit it works with Wi‑Fi off.

Источник

The model runs in a Web Worker through Transformers.js and ONNX Runtime Web, on the CPU.

Источник

The first version scored below chance. That was my bug: I'd prefilled the answer with "Answer:" (trailing space)... Fixed, multiple choice was still worse than the small model alone.

Источник

321 transactions from 65 merchants, sorted in about 3.5 seconds on a laptop CPU; 72 lines from 17 merchants flagged for review; 17 clicks to clear them; 0 lines wrong at the end.

Источник

  • Дата записи: 2026-10-15T09:40:58.543Z