Niklas Lange

Machine Learning System to Predict Phishing Sites Using HTML, URL & Metadata

Tue, 31 Mar 2026 00:00:00 +0000

Abstract

Since the start of the internet, phishing has been a persistent problem, with attempts becoming more sophisticated and common in recent years. Prevention models are therefore needed to classify sites correctly as either phishing or legitimate at scale. This paper builds and compares three ML models — Random Forest, Logistic Regression and K-Nearest Neighbours — and a CNN model, using URL, metadata and HTML features collected from phishing and legitimate websites. The models were evaluated on both historical and modern datasets, with a key finding being that all models experienced significant accuracy degradation on modern data, with ML models dropping by ~30% and the CNN by ~48%, despite performing best on historical data.

Hierarchical Reinforcement Learning for Fraud Detection

Sun, 04 May 2025 00:00:00 +0000

What is this?

This was my final project for CS5841 (Machine Learning), built with three other students while I was studying at Michigan Technological University (MTU). I was the only undergraduate in the group, held my own, and am happy to present the work here.

The team

The report and the work are not mine alone — this was a team project, and everyone below deserves equal credit:

Amirmehdi Moghadamfarid
Samuel Raber
Eric Fosu-Kwabi

Hierarchical Reinforcement Learning Fraud Detection (HRLFD): an adaptive approach

Introduction

Financial fraud detection is a critical task in the modern digital economy. Traditional supervised methods often struggle with imbalanced datasets, where fraudulent transactions are far less common than legitimate ones. This project explores the use of reinforcement learning (Q-learning) combined with decision tree classifiers to detect fraudulent cases more effectively. The goal was to design and evaluate a hybrid model capable of identifying fraud while minimizing false negatives.

Grade Inflation in Scotland

Sun, 09 Mar 2025 00:00:00 +0000

This piece was written for the Strathclyde Telegraph; what follows is the first draft, which I put together over about a week and posted here while the final version went through editing.

Scottish Highers have been a crucial component of university applications for decades, and published results run back to 2009. Given recent economic inflation, this correspondent was curious whether a similar trend exists in Scottish education. Analysing the data published on Scottish Highers reveals some intriguing trends.

Strathclyde's Changing Demographics

Sun, 29 Dec 2024 00:00:00 +0000

I am a big fan of journalism — The Economist in particular — so I thought it would be fun to try a bit of data journalism of my own and pitch it to my university newspaper. I started by looking into the demographics of the University of Strathclyde; what follows is a short report on what changed.

Over the years Strathclyde has been through a lot: Brexit, Covid and strikes may all have left a mark on the university’s make-up and capacity. This report goes to the data to see which trends actually show up.

A Two-Year Web Scraping Pipeline

Sun, 15 Dec 2024 00:00:00 +0000

Summary

This project implements an end-to-end pipeline to collect, store, and visualize publicly available video-ranking data from a major online video platform. The aim was to explore geographic differences in popularity, track trends over different time windows (daily, weekly, monthly, yearly, all-time), and build a robust system that runs on a schedule with monitoring and backups.

Note: the project only collected information that is publicly visible on the site, and used rate limiting and scheduling safeguards to avoid putting load on it. See the Ethics, legal & safety section below for the precautions taken. The pipeline was retired in August 2025, after changes to the site cut the amount of usable data — and the insight that could be drawn from it — significantly.

How Hot is Scotland? – Fires in the Last Decade

Sun, 21 Jul 2024 18:53:38 +0100

Over the past decade, the number of fires in Scotland has been falling. This is an encouraging trend, but there is still room for improvement. The majority of incidents were classified as ‘Not Accidental,’ with the highest concentration in densely populated areas such as Glasgow.

Fires over the last decade

We can see a clear downward trend, particularly after 2010/2011, when the number of incidents began to decline more significantly.

Smoking in Scotland – How Households Have Quit Cigarettes

Thu, 12 Jan 2023 18:53:38 +0100

Trends in Smoking Habits Across Scotland (2012–2019)

From 2012 to 2019, the Scottish Survey Core Question (SSCQ)—a project combining several large household surveys (more here)—was used to track smoking rates across Scotland.

The data shows a clear trend: more and more Scots are quitting cigarettes. While we cannot determine causation from this dataset, we can highlight significant differences across age groups and constituencies. These findings reveal how smoking has declined at different rates within the population.