Relevance

No code interface to customize search rankings

7 followers

No code interface to customize search rankings

7 followers

Relevance is a hosted site search service, with a user interface for building custom ranking algorithms. Users can A/B test new versions of ranking rules and analyze the results, without needing to code.

Launch tags:API•A/B Testing•Developer Tools

Launch Team

Render Sandboxes: a computer for every agentIsolated compute, persistent state and a real filesystem

Promoted

Weave Product Hunt Group

I've had to build this from scratch at every startup. What's is in the analytics tab? I find that often in our haste, we are a less structured than we would like about testing out all the small tweaks we make.

Report

6yr ago

Relevance

Maker

@hsukenooi that was the inspiration behind creating Relevance — we wanted to make it simple to test and improve on your ranking algorithms :) The analytics tab contains helpful data on how users are interacting with your search (e.g., most used filters, most shown results) and how A/B tests are performing

Report

6yr ago

Kickoff

As the founder of a marketplace startup, this product made perfect sense to me from day 1. One pain point we have is proper monitoring of when problems arise in the matching process - insufficient supply in a certain segment, bugs introduced by a change that does not seem related but which tweaks the matching algo in some way. Have you thought about building in problem alerts?

Report

6yr ago

Relevance

Maker

@john_gardner Hi John, we plan on expanding our analytics to help monitor search/match effects all the way through the funnel. This can help you determine why search conversion may be slipping in a certain segment, and insufficient supply can definitely be a culprit. I like the idea of problem alerts to be proactive about letting the user know, thanks for the feedback!

Report

6yr ago

Weave Product Hunt Group

Interesting - what are some examples of things you can tweak as a user? How much is controlled by human vs algo?

Report

6yr ago

Relevance

Maker

@zealoustiger Thanks Brian! You can tweak the importance of different factors in your search algorithm, say average review score vs. number of reviews. Today the tweaking is done by the user (human), but we plan on bringing AI assistance soon (algo) 🙂

Report

6yr ago

The Shoot

Fantastic product @zacharyconn! We implemented Relevance on The Shoot - a marketplace to find and book local photographers in the UK. It was fast to implement and super easy to define and adjust the ranking rules. Relevance transformed the search experience for our customers by pushing higher quality listings to the top. This, in turn, increased conversion and customer satisfaction. Zach has also been super helpful throughout. Highly recommend!

Report

6yr ago

Relevance

Maker

@fi_macdougall Thanks Fiona! It has been great to work with The Shoot to improve search results and conversion 🙂 https://medium.com/@zconn08/how-...

Report

6yr ago

Looking forward to trying this out! It's been a pain trying to get search right, and I like that with Relevance you get full control through the dashboard.

Report

6yr ago

Relevance

Maker

@gamblers_united We're looking forward to having you! That is why we created Relevance — to give full control back to the user, without needing to code 🙂

Report

6yr ago

Marketplace School

It's been great to learn more about search & ranking from you, what you're building with Relevance, and how marketplaces (especially Sharetribe Flex builds) can benefit from it Zach! Hopefully we can use this sometime soon with Studiotime :)

Report

6yr ago

Relevance

Maker

@yoroomie Thanks Mike! It's been great working with you and Everything Marketplaces 🙂 Excited to integrate with Studiotime in the future Search and ranking workshop:

Report

6yr ago

Really excited about this product! I’ve worked In Product Management at multiple marketplaces and this is a constant pain-point. As a PM org, we know that the order of our search results is a critical lever for conversion, brand, and customer loyalty. It’s something we know we need to optimize but it’s always such a challenge to get a clear view from engineering and data science into how our search algorithm works (at my last company it was referred to as “secret sauce”). To be able to determine search ranking criteria and weightings would be HUGE, and to test variations regularly - without engineering (!) - would be a game changer. Looking forward to trying Relevance out!

Report

6yr ago

Relevance

Maker

@kendra_cook Thanks Kendra! Excited to demystify how search works, and make it easy to iterate on your search algorithm 🙂

Report

6yr ago

1 2

Reviews