# PHBench

> PHBench is the first public benchmark for predicting whether a Product Hunt launch will raise Series A funding within 18 months. It maps 67,292 featured Product Hunt posts (2019-2025) to 528 verified Series A outcomes. Launch-day metadata goes in. An 18-month prediction comes out.

## What is PHBench?

PHBench is a machine learning benchmark and dataset for
startup funding prediction. It provides:
- 67,292 featured Product Hunt posts with 61 engineered features
- 528 verified Series A raises within 18 months of launch
- Public train/validation splits and blind test set
- Official evaluation metrics: F0.5, Average Precision, P@k
- A public leaderboard at phbench.com

## Key Findings

- Baseline ensemble model achieves Average Precision of 0.113 (14.5x lift over random)
- Team size × engagement interaction is the strongest predictor
- B2B categories (API, Payments, Fintech) convert at 3x baseline
- Vanilla LLMs (Gemini 2.5 Flash, Gemini3 Flash) achieve AP=0.034 at best — structured ML significantly outperforms zero-shot LLMs on anonymized numerical signals
- The 2020-2021 VC funding boom and 2022-2023 contraction are visible in launch conversion rates

## Dataset

- 288,692 total Product Hunt posts collected (2019-2025)
- 67,292 featured posts (benchmark universe)
- 528 positive labels (Series A within 18 months)
- Class imbalance: 1:126 (0.78% positive rate)
- Matched to Crunchbase via domain resolution
- Anonymized public splits available on request

## Participation

To participate in the benchmark:
1. Request dataset access: benchmark@vela.partners
2. Train a model on phbench_public_train.csv
3. Generate predictions on phbench_public_test.csv
4. Submit predictions CSV to benchmark@vela.partners
5. Results posted to leaderboard at phbench.com

## Research

Paper: PHBench: A Benchmark for Predicting Startup Series A Funding from Product Hunt Launch Signals
Authors: Yagiz Ihlamur (Amazon), Ben Griffin (Oxford), Rick Chen (Oxford)
GitHu https://github.com/ihlamury

## Built By

- Yagiz Ihlamur — Product at Amazon, AI researcher
- Ben Griffin — Researcher at University of Oxford / Vela Partners
- Rick Chen — Researcher at University of Oxford / Vela Partners
- In collaboration with Vela Partners (https://www.vela.partners/)

## Links

- Website: https://phbench.com
- GitHub: https://github.com/ihlamury/vc-market
- VCBench (related): https://vcbench.com
- Vela Partners: https://www.vela.partners/
- Contact: ihlamuryagiz@gmail.com