Update README.md

README.md

@@ -1,67 +1,63 @@
-# (UPDATE IN README.md) Project Title
+**SMS Scam Classifier**
 
-(UPDATE IN README.md)
-Briefly describe the purpose/result(s) of your project, the skills you applied, and the AI4ALL Ignite program.
-
-*EXAMPLE:*
-*Uncovered and meticulously analyzed three distinct biases present in ChatGPT, employing advanced Python techniques and data analysis methodologies, all within AI4ALL's cutting-edge AI4ALL Ignite accelerator.*
+Developed a binary classification model to distinguish between smishing (SMS phishing) and ham (legitimate) messages, applying supervised machine learning techniques in Python as part of the AI4ALL Ignite program.
+This project involved real-world data preprocessing, feature engineering, model training, evaluation, and deployment via Streamlit, all while emphasizing responsible AI practices and collaboration.
 
 
 ## Problem Statement <!--- do not change this line -->
+Every day, thousands fall victim to SMS scams that exploit trust and urgency. Smishing attacks can lead to data breaches, identity theft, and financial loss. Our project tackles this pressing issue by creating an SMS classifier that can automatically detect and flag scam messages before they cause harm.
+
+This work contributes to a safer digital communication environment, raising awareness of AI's role in cybersecurity and prevention.
+## Key Results <!--- do not change this line -->
 
-(UPDATE IN README.md)
-Describe the motivation for this project, why it is relevant, and what its impacts are.
+-Preprocessed and cleaned 5,971 SMS messages into a structured format with binary labels (smishing or ham)
 
-*EXAMPLE:*
-*Given the substantial daily output of responses, the identification and mitigation of ChatGPT's biases become critical, safeguarding both the multitude of users and the far-reaching consequences they may influence.*
+-Engineered key features such as presence of links, phone numbers, and message length
 
-## Key Results <!--- do not change this line -->
+-Trained and evaluated multiple ML models (Logistic Regression, Decision Tree, Random Forest)
 
-(UPDATE IN README.md)
-Enumerate the main results of this project in a list and describe them.
+-Achieved 95.6% accuracy using the Random Forest Classifier
 
-*EXAMPLE:*
-1. *Recorded over 1,000 unique prompts and their responses generated by ChatGPT*
-2. *Identified three biases in ChatGPT's responses*
-   - *When prompted about this world event*
-   - *When prompted about this field of science*
-   - *When prompted about this political party*
+-Deployed the classifier using Streamlit, allowing users to test messages in real-time
+
+-Created a confusion matrix and classification report to assess precision and recall for both classes
 
 
 ## Methodologies <!--- do not change this line -->
 
-(UPDATE IN README.md)
+-Cleaned and vectorized text using TF-IDF
 
-*EXAMPLE:*
-*To accomplish this, we utilized the OpenAI API to interact with ChatGPT, and we designed a custom Python script to generate diverse prompts and collect corresponding responses. The data was then processed and analyzed using pandas, enabling us to detect patterns and biases in the AI model's outputs.*
-*Engineered a Python script to generate over 1,000 prompts and elicit their responses from ChatGPT, utilizing pandas to collect the data. When prompted for solutions to this specific relevant crisis, nearly 80% of ChatGPT's responses promoted a certain worldview.*
+-Engineered custom binary features (e.g., presence of URL or phone number)
 
+-Trained classification models using scikit-learn
 
-## Data Sources <!--- do not change this line -->
+-Evaluated model performance with accuracy, precision, recall, and F1-score
+
+-Deployed the final model using a Streamlit web app interface
 
-(UPDATE IN README.md)
-Include any relevant data sources that were used in your project.
+-Practiced ethical and inclusive AI development throughout the AI4ALL Ignite program
 
-*EXAMPLE:*
-*Kaggle Datasets: [Link to Kaggle Dataset](https://www.kaggle.com/datasets)*
 
+## Data Sources <!--- do not change this line -->
+
+https://data.mendeley.com/datasets/f45bkkt8pr/1
 ## Technologies Used <!--- do not change this line -->
 
-(UPDATE IN README.md)
-List the technologies, libraries, and frameworks used in your project.
+-Python
 
-*EXAMPLE:*
-- *Python*
-- *pandas*
-- *OpenAI API*
+-pandas
 
+-scikit-learn
 
-## Authors <!--- do not change this line -->
+-Streamlit
 
-(UPDATE IN README.md)
-List the names and contact information (e.g., email, GitHub profiles) of the authors or contributors.
+-matplotlib, seaborn (for visualization)
 
-*EXAMPLE:*
-*This project was completed in collaboration with:*
-- *John Doe ([john.doe@example.com](mailto:john.doe@example.com))*
-- *Jane Smith ([jane.smith@example.com](mailto:jane.smith@example.com))*
+-Jupyter Notebook / VSCode
+
+
+## Authors <!--- do not change this line -->
+This project was completed in collaboration with:
+Seonyoung Lee-Seonyoungsyl
+Rupashi Bahl-rupashibahl
+Datt Patel-dattpatel123