This tool models and optimizes user tasks based on real-world behaviors. It transforms individual task models into unified, constraint-driven representations, using examples like Wordle to demonstrate its effectiveness. The tool visualizes task flows for better design and efficiency.

The goal is to develop a system that predicts which movies a user is likely to enjoy based on their preferences and rating history. The project leverages collaborative filtering and exploratory data analysis to understand user behavior and recommend movies in various genres accordingly.

Python-based User Behavior Analysis Project conducted in Google Colab. Explore, analyze, and optimize user experiences. 📊🚀 #DataScience #ProductAnalytics

在线教育平台数据分析项目：用户行为分析、课程推荐系统、流失率预测与可视化展示。

Code and supplementary data for our submission to IEEE ICMLA 2025.

Live viewership analytics using Kafka, PySpark, forecasting, and Grafana dashboards

This repository contains the data and experimental code accompanying the paper: Lüdemann, R., Schulz, A., & Kuhl, U. (2024, November). Generation Gap or Diffusion Trap? How Age Affects the Detection of Personalized AI-Generated Images. In International Conference on Computer-Human Interaction Research and Applications (pp. 359-381)

An AI-driven risk assessment tool that evaluates users' login input data (e.g. timing, user label and behavior) to calculate a dynamic risk score. Features include mock data generation, labeled training sets, weighted scoring, and deep learning-based predictions.

A movie recommendation system is a type of intelligent system that suggests movies to users based on their past preferences and behavior. Project Includes Source Code, PPT, Synopsis, Report, Documents, Base Research Paper & Video tutorials

Exploratory funnel drop analysis using Python and Pandas to understand user behavior across the e-commerce journey — from homepage to checkout. Focused on conversion optimization, cart abandonment, and revenue growth insights.