Rubber Ducky Labs
blog2

Rubber Ducky Labs: The Solution for Recommender System Issues at Large Companies

In today's world, machine learning is becoming increasingly popular, and companies are investing in it to stay ahead of the competition. However, one of the most significant challenges that large companies face when using machine learning is the accurate diagnosis of issues in their recommender systems. Rubber Ducky Labs is a San Francisco-based start-up that provides developer tools for recommender systems at large companies. In this article, we will discuss Rubber Ducky Labs' approach to fixing issues with recommender systems and how it can benefit your company.

The Problem

Large companies that use recommender systems often face issues when trying to diagnose problems. One such problem is when the system recommends products that are not suitable for the current season. For instance, recommending ski jackets in June is not suitable, and it could lead to users being turned off from the platform. The problem is compounded when the team responsible for maintaining the system has no idea why the system is recommending these products.

Rubber Ducky Labs' Solution

Rubber Ducky Labs helps companies to avoid making tone-deaf product recommendations by combining machine learning with human expertise to produce the best product recommendations. The solution was developed from over a hundred conversations to answer the question, "What's going on with my recommender system?" With Rubber Ducky Labs, you can explore your data visually with product images, drill down from aggregate metrics to individual items or user journeys, consolidate and debug your company's business logic, view annual and seasonal trends, facet, segment, filter, and view side-by-side comparisons of models or ranking changes.

The team at Rubber Ducky Labs understands that people with domain expertise - product managers, merchandisers, marketers, growth hackers, and founders - are the ones who need to build intuition and incorporate domain knowledge into their recommender systems. Their vision is to help you do everything from consolidating business logic to previewing side-by-side model comparisons to launching production experiments, all within Rubber Ducky Labs' tools.

Meet the Founders

The co-founders of Rubber Ducky Labs are Georgia Hong and Alexandra Johnson. Georgia graduated with a degree in software engineering from the University of Waterloo, during which time she completed six internships, including Datadog, Cockroach Labs, Instagram, and SigOpt. After graduation, she worked on Security and ML Infra at Meta. Alexandra, on the other hand, has spent eight years in the ML tooling industry, starting with a 4-year stint as the first software engineer at SigOpt. Before founding Rubber Ducky Labs, she worked on recommender systems in fashion tech.

The Rubber Ducky Labs Experience

Rubber Ducky Labs provides a user-friendly experience for companies to build and improve their recommender systems. The interface is clean and easy to navigate, with options to explore data visually using product images, drill down from aggregate metrics to individual item or user journeys, and view annual and seasonal trends. The platform also allows you to consolidate and debug your company's business logic, facet, segment, and filter your data, and view side-by-side comparisons of models or ranking changes.

One of the key features of Rubber Ducky Labs is the ability to combine machine learning with human expertise. With this tool, companies can avoid tone-deaf product recommendations and provide the best product recommendations to their customers. The platform provides quick and efficient solutions to problems like recommending ski jackets in June, ensuring that users are not driven away by irrelevant or off-season recommendations.

Rubber Ducky Labs also offers the ability to launch production experiments within their tools. This feature is particularly useful for product managers, merchandisers, marketers, growth hackers, and founders, who can easily build intuition about and incorporate domain knowledge into their recommender systems.

Technical Details

Rubber Ducky Labs is a fully hosted web app that connects directly to a company's data warehouse on the backend to pull custom metrics and data. This means that there is no need to deploy any services or change any code. Additionally, the web and API are authenticated with Auth0 to keep data safe.

Setting up Rubber Ducky Labs takes only 90 minutes with their first user. The platform also allows users to bring their own model, making it easy for companies to integrate the tool with their existing systems.

Rubber Ducky Labs' founders, Alexandra and Georgia, have over a decade of experience in fashion tech, B2B ML tooling, and high-scale data infrastructure. They are passionate about making the state of the art in machine learning effortless and easy to understand. Their experience and expertise are reflected in the design and functionality of Rubber Ducky Labs.

Conclusion

In conclusion, Rubber Ducky Labs is a promising start-up that offers a powerful solution for companies struggling with their recommender systems. By combining machine learning with human expertise, the platform allows businesses to diagnose and fix issues quickly, saving them time and resources.

The co-founders, Georgia Hong and Alexandra Johnson, have a wealth of experience in software engineering, data infrastructure, and ML tooling. Their passion for making the state of the art in machine learning effortless and easy to understand is reflected in the suite of dream tools they have created.

Rubber Ducky Labs' focus on domain expertise means that their platform is accessible to product managers, merchandisers, marketers, growth hackers, and founders. It allows them to build intuition and incorporate domain knowledge into their recommender systems, making it an invaluable asset to any business.

The platform's easy setup process and user-friendly interface make it a great option for companies of all sizes. Additionally, the fact that it is a fully hosted web app means that there is no need to deploy any services or change any code, which makes it even more convenient.

Overall, Rubber Ducky Labs has the potential to revolutionize the way companies approach their recommender systems. It's a platform that is worth considering for any business looking to optimize their product recommendations and enhance customer experience.