Retail Match Maker
Automated talent–client matching to enable scalable growth.
80% of matches now happen automatically, doubling the number of shifts while freeing the team to focus on sales expansion.
4 Engineers, 1 Product Manager
Too many variables, not enough structure
Each retail client has unique needs when hiring temps: preferred background, grooming standards, brand guidelines, length of assignment... and meeting those expectations required significant human intervention.
Matching the right talent to the right job involved too many variables (availability, skills, experience, location, performance, preferences), much of which was stored informally across spreadsheets, chat threads, and team memory. This made the process slow, inconsistent, and hard to scale.
To deliver a more seamless and self-served experience for clients, we needed to systematically capture and connect all the data points that influence a good match, and build logic that could automate those decisions with confidence.
Understanding how clients think about talent
We conducted in-depth interviews, calls, and pilots with long-term clients to understand how they assess and select talent, and where automation could genuinely help without losing the human touch. These included on-site visits to stores, walkthroughs of live bookings, and tests with clients already familiar with Dweet’s processes.
From these sessions, we uncovered key insights:
1. Clients valued reliability and continuity (“send me the same person as last week”) but lacked tools to do so.
2. Feedback loops were inconsistent, limiting our ability to learn from previous shifts.
3. Heavy dependence on manual placements created bottlenecks and variability in match quality.
We also identified opportunities to capture the talent data in a more structured way, particularly their skill level and brand category experience. These learnings became the foundation for the Retail Match Maker, a system connecting client needs with talent data in a scalable, data-driven way.
Designing a self-learning matching system
We developed the Retail Match Maker as a set of features and data feedback loops that improve match accuracy over time.
1. Client feedback loops
Integrated post-shift ratings directly into timesheets to improve completion rates.
Automatically promoted top performers into Favourites and flagged issues via a Strikes system.
Introduced blocking to prevent repeat bookings with unsuitable talents.
2. Favourite-driven automation
Built a “My Favourites” page where clients can curate, view, and manage preferred talents.
Added logic for My Team Favourites, Brand Favourites, and Dweet Recommended suggestions.
Simplified lists (max 12) and adjusted sorting rules based on recent shifts and performance.
3. Automated booking logic
The system now auto-selects favourites before suggesting new matches.
Scaling human intuition through data
80%+ of all shift matches now supported by algorithmic logic.
21% of shifts auto-booked within the first month — projected to reach 50%.
Favourites adoption doubled, with clients actively curating their talent pools.
Higher feedback completion rates after embedding ratings into timesheets.
Improved match quality and reduced cancellations, leading to faster, more reliable staffing.
Established the foundation for future real-time matching, predictive scheduling, and AI-driven recommendations.
