Scikit-learn
regression
classification
clustering
tabular
linkedin
job-postings
random-forest
decision-tree
kmeans
shap
Instructions to use MichaelYitzchak/Linkedin_Job_Engagement with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Scikit-learn
How to use MichaelYitzchak/Linkedin_Job_Engagement with Scikit-learn:
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("MichaelYitzchak/Linkedin_Job_Engagement", "sklearn_model.joblib") ) # only load pickle files from sources you trust # read more about it here https://skops.readthedocs.io/en/stable/persistence.html - Notebooks
- Google Colab
- Kaggle
Update README_polished.md
Browse files- README_polished.md +15 -0
README_polished.md
CHANGED
|
@@ -130,6 +130,21 @@ The raw `views` variable is highly right-skewed, so `log_views = log(views + 1)`
|
|
| 130 |
> **False Negatives are the most costly mistake.** Missing a genuinely high-engagement posting means the company fails to prioritize a valuable listing. F1-score balances this against False Positives (over-flagging normal postings wastes recruiter attention).
|
| 131 |
|
| 132 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 133 |
|
| 134 |
## 💡 Business Insights
|
| 135 |
|
|
|
|
| 130 |
> **False Negatives are the most costly mistake.** Missing a genuinely high-engagement posting means the company fails to prioritize a valuable listing. F1-score balances this against False Positives (over-flagging normal postings wastes recruiter attention).
|
| 131 |
|
| 132 |
---
|
| 133 |
+
## 🚀 Interactive Dashboard
|
| 134 |
+
|
| 135 |
+
The project includes a deployed Gradio dashboard on Hugging Face Spaces.
|
| 136 |
+
|
| 137 |
+
👉 **[Open the LinkedIn Job Engagement Dashboard](https://huggingface.co/spaces/MichaelYitzchak/linkedin_Job_Engagement)**
|
| 138 |
+
|
| 139 |
+
The dashboard includes:
|
| 140 |
+
|
| 141 |
+
- **Engagement Predictor** — predicts estimated job views and high/low engagement classification.
|
| 142 |
+
- **EDA Dashboard** — interactive charts summarizing the main project findings.
|
| 143 |
+
- **About Tab** — project summary, model details, feature groups, and limitations.
|
| 144 |
+
|
| 145 |
+
|
| 146 |
+
|
| 147 |
+
|
| 148 |
|
| 149 |
## 💡 Business Insights
|
| 150 |
|