ShopCast: a sales forecast a small shop can actually pay for

本文为原文前 6,000 字符的节选翻译，完整内容请查看原文。

ShopCast: a sales forecast a small shop can actually pay for

Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle Submission 💸 This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle What I Built The shop owner already knows Saturday is busy. What they cannot price is how much busier, or what happens if they run a Friday promo, or whether last month’s “slow Wednesday” was just Wednesday. Closed forecasting tools want a seat licence in dollars and the whole sales history on a server they control. For a bakery or mini-mart, that is not a product. That is a cost centre.

Hacktoberfest 开源 AI 挑战赛第 2 周：副业项目提交 💸 这是 Hacktoberfest 开源 AI 挑战赛第 2 周的副业项目提交。我构建的内容：店主已经知道周六很忙。但他们无法估算的是到底忙多少，或者如果他们进行周五促销会发生什么，又或者上个月的“冷清周三”是否真的只是周三。封闭式的预测工具需要以美元计价的席位许可，并将全部销售历史存储在他们控制的服务器上。对于面包店或小型超市来说，这不是产品，而是成本中心。

ShopCast is the version I would actually charge for. Export daily sales as a CSV (date, sales, optional promo). Click Start forecast. You get: the next 1–8 weeks of sales, with a range, not a single smug number unusual days the model did not expect (generator died, surprise catering order) a backtest against the owner’s own rule: “same as last week” a chat box that answers “what if I promo every Friday?” with TabPFN’s numbers, then Gemma’s words Who pays: a shop that would spend a few thousand naira a month to stop over-baking on Tuesdays.

ShopCast 是我真正愿意收费的版本。将每日销售额导出为 CSV（日期、销售额、可选促销）。点击“开始预测”。你将获得：未来 1-8 周的销售额，以区间而非单一自负的数字呈现；模型未预料到的异常日期（发电机故障、意外的餐饮订单）；针对店主自身规则“与上周相同”的回测；一个聊天框，通过 TabPFN 的数据和 Gemma 的语言回答“如果我每周五都做促销会怎样？”。谁会买单：一家愿意每月花费几千奈拉来避免周二过度烘焙的商店。

How I Built It I built this on a five-year-old Latitude: 2-core i5, 8 GB RAM, no usable GPU. About a gigabyte free on a good day. So the first design decision was boring and correct: do not run TabPFN or a 27B model on this laptop. TabPFN goes through Prior Labs. Gemma goes through Google AI Studio. The laptop runs Streamlit and pandas.

我是如何构建它的：我在一台五年前的 Latitude 笔记本电脑上完成了开发：双核 i5，8GB 内存，没有可用的 GPU。状态好的时候大约有 1GB 的空闲内存。因此，第一个设计决策既无聊又正确：不要在这台笔记本电脑上运行 TabPFN 或 27B 模型。TabPFN 通过 Prior Labs 运行，Gemma 通过 Google AI Studio 运行。笔记本电脑仅运行 Streamlit 和 pandas。

The second decision was how to make forecasting tabular. Each day is a row: weekday, payday window, Nigerian public holidays, festive season, promo flag, sales from 7 and 14 days ago. Lags start at 7 on purpose. That way TabPFN predicts a whole week in one call, then those predictions become next week’s lags. Four API calls for 28 days, not 28. Unusual days use the same model in 5-fold out-of-sample scoring.

第二个决策是如何使预测表格化。每一天都是一行：工作日、发薪日窗口、尼日利亚公共假期、节日、促销标记，以及 7 天和 14 天前的销售额。滞后项特意从 7 开始。这样 TabPFN 可以在一次调用中预测整周，然后这些预测成为下一周的滞后项。28 天只需四次 API 调用，而不是 28 次。异常日期使用相同的模型进行 5 折样本外评分。

Why Does Open Innovation Matter? The model vanished and the app did not. Gemma 3 27B 404’d. I listed what the key actually serves and swapped. A closed “forecasting API” with one SKU does not let you do that on a Sunday afternoon. Small data is the product, not the edge case. A bakery has hundreds of daily rows, not millions. TabPFN is built for that. Asking a general LLM to “look at the CSV and predict October” is how you fail.

为什么开放式创新很重要？模型消失了，但应用程序没有。Gemma 3 27B 报错 404。我列出了密钥实际支持的模型并进行了切换。一个只有单一 SKU 的封闭式“预测 API”无法让你在周日下午做到这一点。小数据才是产品，而不是边缘情况。面包店有数百行每日数据，而不是数百万行。TabPFN 正是为此而生。要求通用大语言模型“查看 CSV 并预测十月”是注定会失败的。