-
Spam
-
Not Spam
Inspiration
Finding and marking fishy emails as Spam so that people are secure from scams, phishing, or data breaches.
What it does
Takes email from user as input and classifies whether the mail is "Spam" or "Ham".
How we built it
Trained a Logistic Regression model to classify emails from mail_data.csv dataset as "Ham" or "Spam".
Challenges we ran into
Value errors, data acquisition problems, Training problems
Accomplishments that we're proud of
Training Accuracy = 98% Testing Accuracy = 97% Successfully predicts if mail is Ham or Spam
What we learned
Logistic Regression, sklearn, Classification, Dangers of Spam Mails
What's next for Spam Detection
Deploying and Hosting on public site for people to use for themselves.
Log in or sign up for Devpost to join the conversation.