How AI can help us eat to save the planet
An algorithm explores patterns in recipe texts and matches them with user preferences. This can help guide micro-decisions that can in turn benefit climate-friendly food choices, according to the developer team from CGI.
Our choices in food have a big impact on both ourselves and the world at large. From health considerations to carbon footprint, each of our decisions to purchase and devour certain food groups can echo across the globe.
At the Hack in SAS® Viya® competition, a team from CGI asked themselves the question: Can we design a suggestion engine that can help us make smarter choices for ourselves and the planet? Could focusing less on ingredients such as meat and more on taste patterns or cooking methods result in more climate or health friendly consumer choices?
For this project, we decided to focus on making recommendations that would let the user consider a vegetarian alternative to for example beef, while making sure that the recommendation was an appealing alternative Olov Domeij Hackathon Team Lead CGI
Matching preferences to recipes
To gain access to relevant recipe data, they decided to team up with the startup IQ Chef, a data-based company developing smart digital solutions for meals, health and sustainability, and with Köket.se.
We were looking at the semantics of the recipes - descriptions and cooking instructions - somewhat influenced by Kansei Engineering methods in which you map the description used by consumers to common design features Olov Domeij Hackathon Team Lead CGI
The team explored the recipes using SAS® Visual Text Analytics to find some 800 markers for each recipe and SAS Visual Data Mining and Machine learning to train an algorithm on similarities and patterns in recipes that the meat-based and vegetarian options shared. Using a so-called Factorization Machine in SAS® Viya, the team could start predicting how a user might rate a dish that was vegetarian rather than meat-based.
Olov Domeij sees great potential in using AI to inform and even influence our food consumption in a future where, growing populations and climate challenges are affecting the global ecosystem.
The food industry is huge and many in it are aware that it needs to address these problems and be able to react to other trends in consumer preferences. Applying Artificial Intelligence will be one of the ways to rise to that challenge Olov Domeij Hackathon Team Lead CGI
Challenge
- Influencing food customers at the point of decision making, making it easier for them to make smarter decisions for the common good.
Solution
- A suggestion engine that can help us make smarter climate-friendly food choices.
Benefit
- Helping the food industry develop new choice mechanisms nudging the common good in consumer offerings.
Technologies used
- SAS® Viya® Visual Text Analytics
- SAS® Viya® Visual Data Mining and Machine Learning (Factorization Machine)
About Hack In SAS Viya
In association with Intel and SAS Nordic User Group “Fans”. SAS hosted the competition “Smarter Together” for SAS partners. Here, teams of analysts and data scientists demonstrate the value of open data combined with SAS® Viya ® in the cloud and open source technologies.
SAS provided the SAS® Viya® platform with a number of SAS tools in the cloud for easy access through saasnow.com. The nine participating teams built showcase based on a number of SAS software products including: Visual Analytics, Visual Statistics, Visual Data Mining & Machine learning, econometrics, and optimization.