Rubber Ducky Labs recently launched on Y Combinator’s “Launch YC”.

^{David J. Phillips @davj / 4:30 PM PST • February 8, 2023}

‍

Rubber Ducky Labs is building better recommender systems with machine learning plus human expertise. It helps e-commerce companies avoid tone-deaf product recommendations.

The company is founded by Alexandra Johnson, with a goal to provide the ideal suite of tools that she wishes she had during her extensive work on recommender systems in the ML tooling industry at Fashion Tech companies, SigOpt (YC W15) & more.

HOW IT WORKS

It works by combining machine learning with human expertise to produce the best product recommendations.

If your algorithms recommend ski jackets to your users, in June, when it should probably be recommending a t-shirt, you may benefit from Rubber Ducky Labs.

With the ability to provide, in minutes, an answer as to "why" potentially incorrect recommendations happen, leaders within a company or organization using RDL's tools can quickly determine the cause (did a colleague start a ski jacket campaign purposefully? or is the algo just error-prone?) and find the solution.

The mission of Rubber Ducky Labs is to allow people with domain expertise (product managers, merchandisers, marketers, growth hackers, founders etc.) to easily build intuition about and incorporate domain knowledge into their recommender systems.

They want to help you do everything from consolidating business logic to previewing side by side model comparison to launching production experiments, all within RDL’s tools.

Setup took 90 minutes of time with their first user.

Under the hood, Rubber Ducky Labs is a fully hosted web app that connects directly to your data warehouse on the backend to pull your custom metrics and data. No need to deploy any services or change any code, plus you get to bring your own model! Plus, the web and API are authenticated with Auth0 to keep your data safe.

HOW TO LEARN MORE

For more info, visit their website, and consider contacting the team to discuss your current recommender system to start identifying areas for improvement.

Give them a follow on twitter!