REPOGEO 报告 · LITE
ngruver/llmtime
默认分支 main · commit f74234c4 · 扫描时间 2026/6/3 03:23:13
星标 827 · Fork 178
行动计划告诉你下一步要做什么——按影响力排序、可直接复制粘贴的修改。品类可见性是真正的 GEO 测试:当用户向 AI 提一个不带品牌、本应让 ngruver/llmtime 浮出水面的问题时,AI 是真的推荐了你,还是推荐了你的竞品?客观检查验证 AI 引擎最先权衡的那些元数据信号。自指检查判断 AI 是否还认识你的名字。
行动计划 — 可复制粘贴的修复
3 条由 gemini-2.5-flash 生成、按优先级排序的修改。修完后请把对应条目标记为完成。
- highabout#1Add a concise 'About' description
原因:
复制粘贴的修复LLMTime is a method for zero-shot time series forecasting using large language models (LLMs) by encoding numbers as text and sampling extrapolations as text completions.
- hightopics#2Add relevant topics to improve categorization
原因:
复制粘贴的修复["llm", "large-language-models", "time-series", "forecasting", "zero-shot", "machine-learning", "neurips-2023"]
- mediumreadme#3Add a clear, concise project summary to the README's introduction
原因:
当前# Large Language Models Are Zero Shot Time Series Forecasters This repository contains the code for the paper
复制粘贴的修复# Large Language Models Are Zero Shot Time Series Forecasters LLMTime is a novel method for zero-shot time series forecasting that leverages large language models (LLMs) by encoding numerical data as text and generating future predictions through text completions. This approach allows LLMs to outperform many traditional time series methods without any prior training on the target dataset. This repository contains the code for the paper
本次扫描解析到的品类 GEO 通道:google/gemini-2.5-flash, deepseek/deepseek-v4-flash
品类可见性 — 真正的 GEO 测试
向 google/gemini-2.5-flash 提出的不带品牌问题。AI 推荐了你,还是推荐了别人?
各模型使用同一组问题 — 切换标签对比回答与排名。
- Prophet · 被推荐 1 次
- Exponential Smoothing · 被推荐 1 次
- ARIMA/SARIMA · 被推荐 1 次
- Theta method · 被推荐 1 次
- Naive/Seasonal Naive Forecasts · 被推荐 1 次
- 品类问题How to perform time series forecasting without needing to train a specific model?你:未被推荐AI 推荐顺序:
- Prophet
- Exponential Smoothing
- ARIMA/SARIMA
- Theta method
- Naive/Seasonal Naive Forecasts
- NeuralProphet
AI 推荐了 6 个替代方案,却始终没点名 ngruver/llmtime。这就是要补上的差距。
查看 AI 完整回答
- 品类问题What tools enable large language models for time series prediction tasks?你:未被推荐AI 推荐顺序:
- Hugging Face Transformers (huggingface/transformers)
- PyTorch (pytorch/pytorch)
- TensorFlow (tensorflow/tensorflow)
- Pandas (pandas-dev/pandas)
- Scikit-learn (scikit-learn/scikit-learn)
- Nixtla (Nixtla/nixtla)
- Weights & Biases (wandb/wandb)
- Optuna (optuna/optuna)
- Ray Tune (ray-project/ray)
AI 推荐了 9 个替代方案,却始终没点名 ngruver/llmtime。这就是要补上的差距。
查看 AI 完整回答
客观检查
针对 AI 引擎最看重的元数据信号的规则审计。
- Metadata completenesswarn
建议:
- README presencepass
自指检查
当被直接问到你时,AI 是否还知道你的仓库存在?
- Compared to common alternatives in this category, what is the core differentiator of ngruver/llmtime?passAI 明确点名了 ngruver/llmtime
AI 的回答可能信誓旦旦却是错的。请按事实核对:技术栈、目标人群、差异化点是不是和你实际的对得上?
- If a team adopts ngruver/llmtime in production, what risks or prerequisites should they evaluate first?passAI 明确点名了 ngruver/llmtime
AI 的回答可能信誓旦旦却是错的。请按事实核对:技术栈、目标人群、差异化点是不是和你实际的对得上?
- In one sentence, what problem does the repo ngruver/llmtime solve, and who is the primary audience?passAI 明确点名了 ngruver/llmtime
AI 的回答可能信誓旦旦却是错的。请按事实核对:技术栈、目标人群、差异化点是不是和你实际的对得上?
嵌入你的 GEO 徽章
把这个徽章贴进 ngruver/llmtime 的 README。每次重新扫描都会自动更新,并跳到最新报告——是「我在乎 AI 可发现性」最简单的公开证明。
[](https://repogeo.com/zh/r/ngruver/llmtime)<a href="https://repogeo.com/zh/r/ngruver/llmtime"><img src="https://repogeo.com/badge/ngruver/llmtime.svg" alt="RepoGEO" /></a>订阅 Pro,解锁深度诊断
ngruver/llmtime — 轻量扫描仍免费;本卡列出 Pro 相对轻量的深度额度。
- 深度报告每月 10 次
- 无品牌品类查询5,轻量 2
- 优先行动项8,轻量 3