A machine learning-powered web app that detects whether a job posting is real or fake. Developed to help job seekers avoid online employment scams using natural language processing and supervised learning.
🔗 Hosted App: https://spothescamai.streamlit.app
📺 Presentation Link: https://www.youtube.com/your-video-link
Online job scams are rising rapidly, luring victims through fake offers and fraudulent listings. This app uses a trained machine learning model to classify job descriptions as legitimate or fraudulent, helping users make safer career decisions.
- 🔍 Predicts if a job post is fake or real
- 🧠 ML model trained using Logistic Regression
- 📋 Text preprocessing (stopwords, TF-IDF, etc.)
- 🌐 Streamlit-based interactive frontend
- 🧪 Model trained on real job post dataset
- 📈 F1-Score: 0.88
-pandas -scikit-learn -streamlit -matplotlib -seaborn -plotly -joblib -Pillow -wordcloud -numpy -requests -shap
Due to file size, the trained model and original dataset are hosted externally.
📥 Download Link: https://drive.google.com/your-dataset-and-model-link
After downloading:
- Place
model.pklin themodels/folder - Place the dataset (optional) in the
data/folder
-
Clone the repository:
git clone https://github.com/your-username/spot-the-scam.git cd spot-the-scam -
(Optional) Create a virtual environment:
python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate
-
Install dependencies:
pip install -r requirements.txt
-
Download model file from Google Drive and place it in the
models/folder. -
Run the app:
streamlit run app/app.py
| Metric | Value |
|---|---|
| F1 Score | 0.88 |
| Accuracy | 89.3% |
| Precision | 0.87 |
| Recall | 0.89 |
- Suryansh Mishra — Lead Developer & Data Scientist
- 🔹 Hosted App: https://spothescamai.streamlit.app
- 🔹 Demo Video: https://www.youtube.com/your-video-link
spot_the_scam_project/
│
├── app/
│ └── app.py
│
├── models/
│ └── model.pkl
│
├── data/
│ └── [not included – download from Drive]
│
└── README.md