مواد پر جائیں

Professional networking

حوالہ جاتی نمونہ

Three times the industry connection rate, in 15 milliseconds

A matching engine that models people as vectors across skills, goals, seniority, industry and geography — and returns a ranked, business-rule-aware shortlist in fifteen milliseconds.

3xindustry connection rate

ایک نظر میں

مدت
39 ہفتے
ٹیم کا حجم
4 افراد
معاہدے کی نوعیت
نئی تعمیر
پروجیکٹ کی قسم
ویب ایپلیکیشن
شعبہ
B2B SaaS

صورتحال

مسئلہ

Good matches need signal, and asking users for signal directly means a preference form nobody finishes. Beyond that, naive pairwise matching is O(n²) and stops being computable somewhere around 25,000 users.

ہم نے کیا کیا

Infer the signal from the profile graph, retrieve approximately, then re-rank exactly — which is what keeps the whole thing inside 15ms.

وہ فیصلے جو اہم تھے

  • Approximate retrieval, exact re-ranking

    An HNSW index over pgvector for sub-10ms nearest-neighbour retrieval, then a re-ranking pass applying mutual connections, past interactions and verification status. Precision where it changes the answer, approximation where it does not.

  • Negative feedback as a first-class signal

    Explicit 'not relevant' signals fed back into ranking. This moved the numbers more than any change to the model did.

کیا بدلا

industry average acceptance rate
3xindustry average acceptance rate
end-to-end recommendation latency
15msend-to-end recommendation latency
match relevance
4.3/5match relevance
30-day retention
62%30-day retention
  • 15ms — 12ms retrieval, 3ms re-ranking
  • 4.3/5 — user-reported
  • 62% — at 25K+ monthly actives

Three times the industry-average acceptance rate, 4.3/5 self-reported relevance, and 62% thirty-day retention across 25,000+ monthly actives.

استعمال شدہ خدمات

  • Vector-based matching engine on pgvector with HNSW
  • Business-rule re-ranking layer
  • Feedback instrumentation feeding ranking weights

ہم کیا مختلف کرتے

ہر منصوبے میں ایسی ایک بات ہوتی ہے۔ اسے شائع کرنا ہی اصل نکتہ ہے — جس کیس اسٹڈی میں کوئی پچھتاوا نہ ہو وہ ثبوت نہیں، تشہیر ہے۔

The biggest improvement did not come from a better model, it came from better feedback loops. We would instrument the negative signal on day one rather than adding it once the rankings looked suspicious.

استعمال شدہ خدمات

مزید کام

شروع کرنے کے لیے تیار ہیں؟

ایسا ہی منصوبہ شروع کریںکام