Credit: Dreamstime
Insight Enterprises has built a cloud infrastructure to grow GrainCorp's analytics capability.
Together, Insight helped design the infrastructure with a Microsoft Azure Data Lake and Databricks as the core computation drive.
Additionally, Azure Data Factory was used to orchestrate integration with data sources throughout the agribusiness's systems, while Azure Key Vault was implemented to store sensitive information.
Insight was brought in after GrainCorp approached Microsoft to find a partner to improve its analytics system, which prior to the cloud infrastructure was “very ad hoc”, according to Pip Garner, GrainCorp’s head of analytics.
In fact, analysts would run data models through spreadsheets and send updates to source data via email.
“There was no consistency in our process and we were reliant on individuals to maintain different models,” Garner said. “On top of that, access to data was really challenging.
“We saw the opportunity to [find a technology] partner with better tools to make the process more systemised and repeatable,” she added.
Work began in early 2021 when Insight conducted a data estate assessment so it could understand
“I started to speak to GrainCorp about machine learning, the different tools their teams were using, their pain points and some pathways I had seen working with organisations in the past,” said Julian Wise, principal consultant at Insight.
“I was excited to work with them, especially considering the importance of food security globally. Whether you’re looking at the floods in Australia or the war in Ukraine, anything we can do to get food distributed around the world more effectively is for the better.”
During the early stages, 25 use cases were highlighted that could utilise the cloud infrastructure, with the two companies settling on its freight optimisation model to be the pilot project.
“The [original freight optimisation] solution was working in a technically immature way, running locally on a single server, but it worked,” said Wise. “There was a lot of manual work, and it ran slowly.
“GrainCorp knew there was a way to improve the operations, speed up the calculations, standardise the workflow and integrate it with their systems to remove the manual work from performing the calculations.”
The cloud platform was combined with a proprietary routing algorithm to create a prototype, which included a workflow that could update the central data store when analysts updated a spreadsheet with updated grain silo volumes.
“It only took us about 12 weeks to get from the first ideation of what the model would look like to a minimum viable product,” said Garner.
“We try and find the cheapest and most efficient route anyway – we don’t like to waste time and energy.”
The cloud infrastructure can adapt to new solutions as well, as GrainCorp has deployed another model focused on matching supply and demand without overcommitting stocks that will be needed over a 12-month period.
This was formed out of two predictive models – one to recommend which stocks to keep and one to identify where they need to be kept – to meet anticipated demand.
“It can effectively tell you that you need to retain 30,000 tons of high-protein wheat for a specific customer that’s going to call on it in six months’ time,” Garner said.
“That’s not something that you would expect any individual to be able to predict, based on the size and complexity of our network. We’ve been really happy with the accuracy of that strategic tool.
“We’ve got a significant pipeline of use cases that we’d love to deliver, adding more value for the business and helping with that decision-making process, by providing better analytics and more robust decision-making across the value chain,” she added.
Last year, Insight won work with TAFE NSW to implement a platform to serve as a new "backbone" and the Western Australian government’s Department of Water and Environmental Regulation (DWER) to streamline water and environmental regulatory approvals, the latter of which being worth $23 million.
