200K
KG of food saved from landfills to date
70%
Reduction in food waste for key clients
<
Fewer harmful GHG emissions
Orbisk gives foodservice providers better visibility into their food waste streams, empowering them to make data-informed decisions about their food supply chains. They partnered with Sama to label the data that fuels their AI-powered food waste monitoring solution, empowering chefs and restaurant managers with data-driven insights to help them shrink food waste by as much as 70%.
Massive datasets and diversity of labels
Massive number of ingredients to be labeled: vegetables, fruit, bread, sauces, meat — in a variety of shapes, sizes, angles, and preparation styles.
Need for tight feedback loops
To reach consistent attribute tagging, Orbisk needed labelers who could iterate rapidly on instructions and effectively become experts on their data.
Flexible workflows to provide timely reports
Providing timely and accurate reports requires flexible workflows that can manage a constant influx of data.
{{ testimonial-1 }}
Sama worked with Orbisk to deliver high-quality labeled data to power their technology, accurately labeling hundreds of thousands of food images.
Open feedback loops enabled the rapid escalation and resolution of edge cases and accommodation of new data sources.
Finally, Sama APIs helped streamline the data annotation and delivery process so customers can receive accurate reports in a timely manner.
{{ testimonial-2 }}
Accurately labeled data provided by Sama now powers Orbisk’s technology, giving foodservice providers readily available insight into which foods they are wasting most often, allowing them to better manage their budgets and waste levels.
With this reduction in food waste comes significant cost savings and a measurable impact on the environment.
You can imagine the heaps of images coming in from the restaurants that we work with. Most are identified by image recognition algorithms, but for outliers and edge cases, we rely on Sama.
Sama’s agents became increasingly better at labeling our data thanks to feedback loops. This iterative way of working has made them experts on our data.