October 19th, 2022

AI for Good: PetFinder.my Levels Up Furry Matchmaking

RSS icon RSS Category: AI4Good, Driverless

Nothing tugs at the heart strings quite like a poster in your neighborhood about a missing cat or dog. For years, technology has enabled lost pets to be reunited with their families in the form of a small microchip that contains an owner’s contact information. Now some organizations are turning to emerging technology to help the millions of strays and surrendered animals around the world each year.

PetFinder.my in Malaysia (not affiliated with Petfinder in the United States) is turning to data science and artificial intelligence to help find forever homes for the more than 23,000 stray and abandoned animals currently on their platform, building upon extensive data of over 200,000 pet profiles and 14 years of user interactions.

“Pet adoption is just like matchmaking, connecting two parties into a happy relationship — in this case, a furry four-legged one with a human,” said Andy Koh, CEO of PetFinder.my. “Technology is evolving so quickly, it only makes sense that we turn to data science and artificial intelligence now. Using data science, there are now more ways to improve animal welfare, such as enhancing the pet profiles, photos and recommendations.”

The organization leverages a technology donation from H2O.ai, a Silicon Valley-based company, founded on the idea that AI should be accessible to everyone and that the power of AI should be used to better society.

H2O.ai’s models help PetFinder.my analyze a range of intrinsic points such as age and breed, and extrinsic points like photos and biographies and profiles to predict an animal’s appeal for adoption. The tool can help provide recommendations to optimize the chance of pet adoption and the speed at which the animal can find a new home. Computer vision models are also being explored to analyze the content and visual appeal of pet photos, applying machine learning to generate automated enhancements and recommendations on capturing better photos.

Koh believes AI models can double adoption rates and improve efficiency, helping animals find new homes in less than a month, rather than the 60-plus timeline animals face now. Speeding up the adoption process improves the quality of life for the cats and dogs, but it also significantly reduces the animal shelters’ costs in caring for stray cats and stray dogs every year.

“H2O.ai’s  Driverless AI (DAI) is an amazing tool for comprehensive analysis of our data, speedy visualizations and prototyping to determine what strategies and features would be most useful for our models,” said Koh. “We have so much data that we are often unsure of which fields, features or relationships are most relevant for a specific goal, and DAI allows us to easily execute a wide range of experiments and fine-tune them.”

Koh hopes to expand his team with volunteer data scientists to help improve their models and production system. Like all non-profits, raising funds is a critical, yet challenging, part of the job– especially during the COVID-19 pandemic, so volunteers play a key role in their operations. 

To learn more about PetFinder.my and their mission, visit their websiteFor more information on H2O.ai’s AI 4 Good initiative, visit their website.

About the Author

H2O.ai Team

At H2O.ai, democratizing AI isn’t just an idea. It’s a movement. And that means that it requires action. We started out as a group of like minded individuals in the open source community, collectively driven by the idea that there should be freedom around the creation and use of AI.

Today we have evolved into a global company built by people from a variety of different backgrounds and skill sets, all driven to be part of something greater than ourselves. Our partnerships now extend beyond the open-source community to include business customers, academia, and non-profit organizations.

Leave a Reply

H2O LLM DataStudio Part II: Convert Documents to QA Pairs for fine tuning of LLMs

Convert unstructured datasets to Question-answer pairs required for LLM fine-tuning and other downstream tasks with

September 22, 2023 - by Genevieve Richards, Tarique Hussain and Shivam Bansal
Building a Fraud Detection Model with H2O AI Cloud

In a previous article[1], we discussed how machine learning could be harnessed to mitigate fraud.

July 28, 2023 - by Asghar Ghorbani
A Look at the UniformRobust Method for Histogram Type

Tree-based algorithms, especially Gradient Boosting Machines (GBM's), are one of the most popular algorithms used.

July 25, 2023 - by Hannah Tillman and Megan Kurka
H2O LLM EvalGPT: A Comprehensive Tool for Evaluating Large Language Models

In an era where Large Language Models (LLMs) are rapidly gaining traction for diverse applications,

July 19, 2023 - by Srinivas Neppalli, Abhay Singhal and Michal Malohlava
Testing Large Language Model (LLM) Vulnerabilities Using Adversarial Attacks

Adversarial analysis seeks to explain a machine learning model by understanding locally what changes need

July 19, 2023 - by Kim Montgomery, Pramit Choudhary and Michal Malohlava
Reducing False Positives in Financial Transactions with AutoML

In an increasingly digital world, combating financial fraud is a high-stakes game. However, the systems

July 14, 2023 - by Asghar Ghorbani

Ready to see the H2O.ai platform in action?

Make data and AI deliver meaningful and significant value to your organization with our state-of-the-art AI platform.