Back To Projects

Identifying EOL software

Neal D.

Throughout our project, we have been exploring ways to identify EOL and malicious websites using python. Creating a new variable with the keywords, we were able to correctly predict 99% of the EOL websites using the data given to us.


Throughout our project, we have been exploring ways to identify EOL and malicious websites using python. With this software, we can help people stay away from these types of websites. There are lots of cybersecurity problems in the world, but we wanted to address the EOL problem because it is something that is within the realm of what we are learning (language recognition), and it has a practical use in the world. We used multiple different commands to identify certain “keywords,” with the intention of getting the highest possible accuracy percentage. We also prioritized the elimination of false negatives over false positives. Creating a new variable with the keywords, we were able to correctly predict 99% of the EOL websites using the data given to us. We were able to conclude that mixing the 2 most important data columns and creating one variable to determine both of the variables is the best way to go about creating a variable that gives you the most.

Explore More!

Neal D.
Clayton Greenberg
Teaching Professor from UPenn

Related Projects

Applying Machine Learning to Historical Cyber Attack Data to Predict and Prevent Future Attacks

This research demonstrates that machine learning algorithms can leverage historical data to predict the nature and severity of future cyber attacks with reasonable accuracy, revealing that despite the sophistication of state-sponsored actors, their attack patterns often exhibit digital fingerprints that offer valuable clues for anticipating future threats amidst global geopolitical tensions.
Isabella F.
Mentored by Simeon Sayer
Relationship of Factors that Determine Tweet Virality

This paper addresses a growing dilemma: As Twitter becomes ever more influential in the modern landscape, predicting what will go viral can help in the discovery and pushing of new ideas and mitigation of risks associated with online networking.
Shawn Z.
Mentored by Shreyas Ramesh
Optimizing Student Success Predictions using Artificial Intelligence

This work investigates using AI and neural networks to enhance predictions of student success and optimize resource allocation in education, finding that advanced models can significantly improve support for students and address resource imbalances.
Sameeksha V.
Mentored by Jose Reyes