Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/ihmissuti/hacker-ai
Pre-test Hacker News Show HN post subtitles with machine learning algorithm
https://github.com/ihmissuti/hacker-ai
Last synced: about 2 months ago
JSON representation
Pre-test Hacker News Show HN post subtitles with machine learning algorithm
- Host: GitHub
- URL: https://github.com/ihmissuti/hacker-ai
- Owner: ihmissuti
- Created: 2020-11-26T11:41:28.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2021-01-31T19:34:26.000Z (over 3 years ago)
- Last Synced: 2024-05-08T13:33:07.790Z (5 months ago)
- Language: JavaScript
- Size: 181 KB
- Stars: 20
- Watchers: 2
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Hacker-AI
This is an example repo of hacker-ai.com
Hacker-AI is a tool for pre-testing your Show HN titles and Product Hunt texts.
## How it works
Visit https://www.hacker-ai.com and enter your Show HN title variations and see which one has higher chance of winning according to the neural network.
## Under the hood
Hacker-AI uses a brain.js feed-forward neural network machine learning model. The example in this Github repo uses a dataset that contains all stories and comments between 2006 and 2017.
https://www.kaggle.com/hacker-news/hacker-newshttps://github.com/HackerNews/API/blob/master/LICENSE
The live site hacker-ai.com updates it's data monthly from Hacker News API and Product Hunt API.
## Accuracy
The algorithm has been able to predict 60%-70% of the cases correctly when used together with bag-of-words analysis.