AI Home Search
ROLE
Product Strategy Visual Design UX Design User Research
TIME
3 sprints
DATE
Nov 2023
INTRO
I led the design and implementation of an AI-powered search feature. By leveraging natural language processing, we extracted key property attributes and combined these insights with a personalized “match score” system derived from user preferences.
PROBLEM
Traditional real estate websites rely heavily on structured data, such as price, beds, and baths, limiting users' ability to search by personal preferences like natural light, architectural style, or proximity to grocery stores. Users had to manually read through property details paragraph and images on each listing, making the home-searching experience tedious, time-consuming, and often frustrating.
USER RESEARCH
User Interview
We interviewed prospective homebuyers and current customers to understand which attributes mattered most but were missing from typical search filters. Participants frequently cited lifestyle-related factors like proximity to grocery stores, ambiance of a neighborhood, or the “feel” of natural light in a home.
MLS Data Analysis
We then conducted an AI-powered analysis of over 10,000 property listings, focusing on unstructured data fields (agent remarks). This helped us map out how often key attributes appeared, so we could design our questionnaire around fields that were both high-value to users and frequently mentioned in listings.
Preference Questionnaire
Based on these findings, we created a questionnaire flow that captured users’ unique preferences. We included high-coverage attributes (e.g., “close to schools,” “modern style”) and some lower-coverage but high-value ones (e.g., “lots of natural light,” “nearby restaurants”) to account for various user needs.
HYPOTHESIS
We believed that systematically capturing user preferences and converting unstructured listing descriptions into structured data would lead to:
Higher Engagement – Users would be more engaged when searching because relevant results surfaced faster.
Increased Tour Requests – With a tailored set of listings, users would be more inclined to schedule tours.
Better Lead Generation – An interactive and personalized quiz would draw in potential buyers, improving the conversion rate from site visitor to lead.
SOLUTION
Our design solution centered on creating a seamless, user-friendly home-finding experience powered by AI. We designed a simple questionnaire that guided users through key lifestyle and home preference questions, with progress indicators and contextual prompts to improve engagement and understanding. On the backend, we leveraged ChatGPT and ScaleAI to analyze agent remarks, extracting hidden attributes like “lots of natural light” or “big backyard” to enrich property listings. A personalized match score algorithm then translated user preferences into ranked results, ensuring top matches surfaced while preserving choice flexibility. Through iterative design reviews and user testing, we refined question clarity, attribute selection, and result presentation to enhance usability and decision-making.
QUESTIONNAIRE FLOW
A simple, intuitive series of questions about lifestyle preferences and home features. Progress indicators and optional “skip” buttons to reduce drop-off. Contextual prompts that educated buyers on why we asked each question (e.g., “Proximity to groceries can save you time and boost convenience”).
AI PROCESSED LISTINGS
We utilized ChatGPT + ScaleAI to parse agent remarks for hidden attributes. A dedicated back-end service tagged each listing with structured fields like “lots of natural light” or “big backyard.”
MATCH SCORE ALGORITHM
Each user’s questionnaire responses were translated into a preference profile. Our system calculated a personalized “match score” for every listed property, sorting results to highlight top matches without entirely excluding lower-scoring ones, mitigating the “fear of missing out.”
TESTING
Usability Testing
We tested the questionnaire with a pilot group of homebuyers to gauge clarity and flow. Feedback led to the creation of short tooltips explaining certain real estate terms (e.g., “What does ‘open concept’ mean?”).
A/B Testing
We compared the AI-Based Search flow against the existing search experience. Key performance metrics included completion rates, user satisfaction scores, and percentage of users who requested an in-person tour.
Refining the Algorithm
Adjusted weighting in the match score based on user feedback—some discovered “nice-to-have” features shouldn’t overshadow fundamental preferences like location or price range.
IMPACT
Higher Questionnaire Completion
83% of existing users completed the new preference questionnaire, indicating strong interest in more personalized search results.
Improved Tour Rate
A 46% bump in tour rate (the percentage of users requesting an in-person tour after browsing) showed that more relevant results translated into tangible action.
Boosted Lead Generation
Using this flow with Google Ads nearly doubled our sign-up conversion rate, from 7.14% in the old funnel to 13.88% in the new AI-based quiz flow.
Enhanced User Satisfaction
Qualitative feedback highlighted how users appreciated the deeper insight into listings, especially for less obvious features like property layout or nearby amenities.
Flyhomes' AI-based search fundamentally changed how users interact with real estate listings. By transforming unstructured data into structured, actionable insights and personalizing the search experience, we not only improved user satisfaction but also substantially increased engagement and conversion. This innovation sets a new standard in real estate search technology, highlighting the powerful potential of AI-driven design.