Pathway Intelligence: Forecasting Interactive Journey Effectiveness on FreeFuse

FreeFuse is an AI-powered platform for building interactive, multi-path digital experiences. As the company expands into personalized content journeys and Agentic AI assistance, there is growing interest in understanding which types of interactive pathways lead to higher engagement and long-term user retention. This project will focus on analyzing and forecasting content journey effectiveness using structural data and behavioral metrics from FreeFuse pathways. In addition to traditional engagement data (e.g., completion rates, drop-offs), students will explore time-to-decision—how long a user takes between choice points—as a signal of content clarity, complexity, and user confidence. Learners will apply data science, predictive modeling, and visualization techniques to identify high-performing pathways, segment engagement styles, and forecast content success based on journey composition and user behavior.

Growth Signals Engine – Early Indicator Analysis for Partner Performance

Core Path Partners seeks to empower its ecosystem of partner organizations by identifying leading indicators of transformation, growth, or risk across multiple operational and behavioral data points. This project invites students to create a signal detection framework that identifies early markers of success or concern based on patterns in simulated or historical partner performance data. Rather than relying on lagging indicators (e.g., revenue drop), this model would surface real-time soft signals like reduced initiative velocity, engagement drop-offs, or stalled milestone progress—enabling preemptive advisory action.

AI Model Optimization for Data Refinement

This project focuses on improving data preparation and AI model training techniques to enhance predictive accuracy. The goal is to create a systematic process for refining datasets, ensuring high-quality input for AI models used in various business applications. Students will analyze data pre-processing methods, evaluate how data inconsistencies impact model performance, and develop an optimized approach to dataset curation. This project is best suited for computer science, AI, or data science students with experience in machine learning and data engineering.

Interactive Content Engagement Strategy Development for FreeFuse

FreeFuse aims to enhance user retention and platform engagement through a data-driven interactive content strategy. This project involves analyzing user behavior to identify engagement trends and improvement opportunities. Interns will develop interactive content prototypes tailored to user preferences and test engagement tactics to optimize user experience. By applying user experience design, data analysis, and content creation, learners will provide actionable recommendations that improve interaction rates and platform effectiveness.