ChicagoDoes is an interactive city-discovery map developed with Ateema that
surfaces Chicago restaurants, attractions, parks, and venues. The platform presents an
identical experience to every visitor despite collecting rich GA4 behavioral telemetry.
This capstone designed and deployed a personalized location-recommendation system
that converts those events into a weighted hybrid ranker combining content similarity,
item–item and user–user collaborative filtering, session co-visitation, transition graphs,
and event-time trending, with Maximal Marginal Relevance diversification and
behavioral-archetype cold-start handling. A leakage-safe offline evaluation over 120
returning users benchmarked the ranker against popularity, content-only, and
collaborative baselines; a weight search validated by five-fold cross-validation improved
held-out NDCG@10 by roughly 20 percent. The interface was redesigned around media-
rich cards whose photographs and listing links are scraped with Firecrawl, and a
feedback-loop guard keeps recommender-driven clicks from re-entering the training data
as organic engagement.
Watch the team present this project at 01:16:25 in the session recording here.
Keywords: recommendation systems, hybrid recommender, collaborative filtering, TF–
IDF, implicit feedback, Maximal Marginal Relevance, cold-start, offline evaluation,
tourism analytics, GA4
Faculty Advisor
Sanjay Boddhu is the Head of AI/ML Engineering at HERE Technologies, a global leader in location data and platform services. He has over 15 years of experience in leading and mentoring diverse and distributed teams in developing state-of-the-art applications and solutions in the domains of Computer Vision, Image Processing, Natural Language Processing, Predictive Analytics, and Data Science Strategy/Modeling. He holds a Ph.D. in Computer Science and Engineering from Wright State University and is a Senior Member of the IEEE.
At HERE, he is leading the UniMap Automation initiative, which leverages AI and machine learning to transform raw spatial and nonspatial data from various sources, such as imagery, probe data, car camera feeds, lidar, and IoT data, into an actionable, navigable digital map that is updated in near real-time. He is also responsible for designing and deploying algorithms at scale, managing product roadmaps and stakeholder engagements, and driving innovation and excellence in map automation and computer vision. His mission is to revolutionize how maps are created and maintained, and to enable new use cases and opportunities for autonomous and robotic mobility.