My first project with Muddy Gecko was to design an infographic for Micron. Delighted to have a new project after the Covid slow-down, I didn't want to take a break even if I had a family camping trip planned. I knew there'd be plenty of down time between fishing, kayaking, picnics, hiking, cooking and campfires.
Power would NOT be a problem, either. I bought this handy solar charger and portable battery so I could keep my Mac charged up (and everyone else appreciated it to keep their devices alive as well).
We were at a campground attached to a resort on San Juan Island, and I could connect to the general store wi-fi once a day to share updates with the client.
Logistics handled, now onto the design process.
Kick off for this project occurred a week before hitting the road. Having never worked on Micron before, I had the chance to brush up on their brand, meet with their creative team for tips, and review guides, aesthetic, photography and artwork. So many factors contribute to a brand, and they had some really awesome elements to work with. Micron had just gone through a re-brand so there wasn't much existing content to be inspired by as I started the design process.
The concept of the infographic was to explain how a recommendation engine works. I first set the stage with some examples of how we actually use online recommendations, and how much data is online to sort through for making recommendations.
For this firs section, I used the newly developed magenta to cyan gradient (always to be used at an angle) with photography from Micron's digital library.
The next step was to explain how a recommendation engine works. Using this illustration of connectivity to represent collection, I thought that showing a transition to meaningful connections that fell into categories (these three columns) to explain filtering the data.
Once the data is sorted into categories, I developed these illustrations to visualize training the data with AI and ML to recognize patterns to make suggestions for content to display.
Once the recommendation is made, and content interacted with, the recommendations are even more accurate to each person. All of our clicks lead to what the engine shows us next.
This last step in the process deals with how data is optimized based on activity for future recommendations. I used a color system to differentiate activity.
Now we had to bring the reader back around to how Micron is the right product to power the best recommendation engines. A more powerful computer makes for an even more sophisticated engine. The backdrop of this diagram is an image of Micron servers, and I envisioned this progression upward toward more increasing complexity.