Spam Filtering Using Supervised Machine Learning Algorithms

The objective of this project is to detect Spam and ham messages using various supervised machine learning algorithms like Naive Bayes, Support Vector Machines algorithm, Bidirectional LSTM, and Transfer Learning with USE Encoder and compare their performance in filtering the Ham and Spam messages. As people indulge more in Web-based activities, and with rising sharing of private-data by companies, SMS spam is very common. Scammers create fraudulent text messages to deceive you into giving them your personal information, such as your password, account number, or Social Security number. If they have such information, they may be able to gain access to your email, bank, or other accounts. SMS spam filter inherits much functionality from E-mail Spam Filtering. Comparative study is performed based on the performance of various supervised learning algorithms and the algorithm that gives us the most accurate result is recommended. A simple UI is developed to demonstrate the working of spam filtering in practice.

Salient Features:
– Text processing using NLP
– Data analysis and visualization
– Performance comparison of multiple different ML/DL algorithms
– Recommendation of the best algorithm for spam filtering task
– Interactive UI to display the output

Tech Stack:
Deep Learning Frameworks, Numpy, Pandas, Scikit Learn, Matplotlib, Seaborn, Python, Flask

Industry:
IT, Software Network