TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Ask HN: Benchmarks for models other than LLMs

5 点作者 caydenm大约 1 年前
I have seen some amazing benchmarks used to rank LLMs abilities, it got me thinking are there similar benchmarks for propensity modelling, churn prediction or other types of models?<p>Are there best practices for comparing model performance beyond benchmark data when they may have different underlying datasets?

1 comment

luke-stanley大约 1 年前
On PapersWithCode, different datasets have benchmarks: <a href="https:&#x2F;&#x2F;paperswithcode.com&#x2F;datasets" rel="nofollow">https:&#x2F;&#x2F;paperswithcode.com&#x2F;datasets</a><p>You can also break down by task here: <a href="https:&#x2F;&#x2F;paperswithcode.com&#x2F;sota" rel="nofollow">https:&#x2F;&#x2F;paperswithcode.com&#x2F;sota</a><p>For churn, you might go to time series forecasting first: <a href="https:&#x2F;&#x2F;paperswithcode.com&#x2F;task&#x2F;time-series-forecasting" rel="nofollow">https:&#x2F;&#x2F;paperswithcode.com&#x2F;task&#x2F;time-series-forecasting</a><p>They have this subtask which is a bit different because it&#x27;s about novel products rather that continued sales, for example:<p><a href="https:&#x2F;&#x2F;paperswithcode.com&#x2F;task&#x2F;new-product-sales-forecasting" rel="nofollow">https:&#x2F;&#x2F;paperswithcode.com&#x2F;task&#x2F;new-product-sales-forecastin...</a><p>But you get the idea of how they organise by task. I&#x27;m curious about other benchmarks and interfaces too and would like to see others.<p>I think HuggingFace and Kaggle have some overlap with different tasks that have benchmarks.