How can Swing Education improve its substitute teacher matching algorithm to reduce unfilled requests?

Introduction

Improving Swing Education's substitute teacher matching algorithm to reduce unfilled requests is a critical challenge that directly impacts the education ecosystem. This problem touches on the core value proposition of the platform and has far-reaching implications for schools, teachers, and students. I'll approach this by examining user segments, analyzing pain points, generating solutions, and proposing metrics to measure success.

Step 1

Clarifying Questions

• Looking at the product context, I'm thinking about the scale of the problem. Could you share what percentage of substitute teacher requests currently go unfilled?

Why it matters: This helps quantify the problem and set benchmarks for improvement. Expected answer: Around 15-20% of requests go unfilled. Impact on approach: A high percentage would suggest a need for major algorithm overhaul, while a lower percentage might indicate fine-tuning.

• Considering user behavior, I'm curious about the typical lead time for substitute teacher requests. How far in advance are most requests made?

Why it matters: This affects the time window for matching and could reveal opportunities for proactive matching. Expected answer: Requests range from same-day to a week in advance, with most falling 1-3 days ahead. Impact on approach: Short lead times might require real-time matching capabilities, while longer lead times allow for more complex optimization.

• Thinking about external factors, I'm wondering about the seasonality of substitute teacher demand. Are there specific times of the year when unfilled requests spike?

Why it matters: Seasonal patterns could inform algorithm adjustments and resource allocation. Expected answer: Higher demand during flu season and end-of-semester periods. Impact on approach: We might consider dynamic algorithm parameters that adjust based on seasonal demand.

• Regarding product lifecycle, where does Swing Education stand in terms of market penetration? Are we looking at expanding to new regions or deepening presence in existing markets?

Why it matters: This influences whether we focus on scaling the existing system or optimizing for current users. Expected answer: Established in several major markets, looking to expand to mid-sized cities. Impact on approach: Balancing optimization for current users with scalability for new markets.